Voice processing method, intelligent terminal and storage medium

Abstract

The invention provides a voice processing method, an intelligent terminal and a storage medium, and the voice processing method can be applied to the intelligent terminal, and comprises the steps: S1, determining a corresponding translation processing strategy according to an obtained speech scene; and S2, executing corresponding translation processing work on the to-be-processed voice according to the translation processing strategy. According to the technical scheme, a speech translation function with speech scene perception can be provided, the problem that a translation result does not conform to the context due to the fact that a traditional speech translation mode lacks speech scene perception is solved, and then the user experience can be improved.

Description

Technical Field

[0001] This application relates to the field of terminal technology, specifically to a voice processing method, a smart terminal, and a storage medium. Background Technology

[0002] In some implementations, speech translation mainly relies on speech recognition (ASR) and machine translation (NMT) technologies to first convert speech into text and then translate it into a specific language.

[0003] In conceiving and implementing this application, the inventors discovered at least the following problems: traditional speech translation methods lack awareness of the speaking context, which may lead to translation results that do not match the context.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a speech processing method, a smart terminal, and a storage medium, which improves the adaptability of speech translation results to context, making the speech translation results more accurate and thus enhancing the user experience.

[0006] This application provides a speech processing method applicable to smart terminals, comprising the following steps: S1: determining a corresponding translation processing strategy based on the acquired speech scenario; S2: performing corresponding translation processing work on the speech to be processed according to the translation processing strategy.

[0007] Optionally, the method for obtaining the speaking scenario includes at least one of the following: The speaking scenario is obtained based on the received setting instructions; The speaking scenario is obtained based on at least one of the speech features corresponding to the speech to be processed, transaction arrangement information, and environmental perception data. Voice features include at least one of the following: number of speakers, keywords, content text, and dialogue structure.

[0008] Optionally, step S2 includes: performing content translation processing on the speech to be processed according to the content translation strategy corresponding to the speaking scenario to obtain translation results; and applying the translation results according to the translation result processing strategy corresponding to the speaking scenario.

[0009] Optionally, the content translation strategy includes at least one of the following: Obtain a basic terminology database corresponding to the speaking scenario; Obtain contextual knowledge information corresponding to the speaking scenario; Associate the basic terminology database with the custom terminology database to obtain terminology database association information; Based on contextual knowledge, a basic terminology database, and / or related terminology database information, the speech to be processed is translated to obtain the translation result.

[0010] Optionally, the method of obtaining the custom terminology database includes at least one of the following: Identify the target users corresponding to the speaking scenarios, and use the personalized terminology library associated with the target users as the custom terminology library; Identify additional topics and use the professional terminology database corresponding to the additional topics as a custom terminology database.

[0011] Optionally, the translation result processing strategy includes at least one of the following: The translation results are displayed according to a target display strategy that matches the speaking context. Obtain the event record file based on the event record template corresponding to the speaking scenario and the translation results.

[0012] Optionally, the target display strategy includes at least one of the following: Display the text information corresponding to the translation result according to the target screen display mode corresponding to the speaking scenario; Play the translated audio corresponding to the translation result.

[0013] Optionally, the speech processing method provided in this application further includes at least one of the following: Obtain transaction arrangement information from the transaction log file; Display transaction arrangement information; The target application is determined based on the transaction attributes and preset association information corresponding to the transaction arrangement information, and the target application is controlled to record or process the transaction arrangement information.

[0014] This application also provides a smart terminal, including: a memory and a processor, wherein the memory stores a voice processing program, and when the voice processing program is executed by the processor, it implements the steps of any of the voice processing methods described above.

[0015] This application also provides a storage medium storing a computer program that, when executed by a processor, implements the steps of any of the above-described speech processing methods.

[0016] As described above, the speech processing method of this application can be applied to smart terminals, including the following steps: S1: Determine the corresponding translation processing strategy based on the acquired speech scenario; S2: Perform corresponding translation processing on the speech to be processed according to the translation processing strategy. Through the technical solution of this application, speech scenarios can be identified and corresponding target translation processing strategies can be configured according to the speech scenario. This allows for the translation processing of the speech to be processed using a target translation processing strategy adapted to the speech scenario, making the translation results more consistent with the actual context, avoiding or reducing translation deviations, and thus making the translation results more in line with the user's expression logic and habits in specific scenarios, thereby enhancing the user experience. In this way, the technical solution of this application can provide a speech translation function with speech scenario awareness, solving the problem of traditional speech translation methods lacking speech scenario awareness, resulting in translation results that do not match the context, and thus improving the user experience. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0018] Figure 1 A schematic diagram of the hardware structure of a mobile terminal to implement the various embodiments of this application.

[0019] Figure 2 This is a communication network system architecture diagram provided for an embodiment of this application.

[0020] Figure 3 This is a flowchart illustrating the speech processing method according to the first embodiment.

[0021] Figure 4 This is a flowchart illustrating the speech processing method according to the second embodiment.

[0022] The realization of the objectives, functional features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0024] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0025] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, may be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of a feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or," "and / or," "including at least one of the following," etc., used in this application may be interpreted as inclusive, or mean any one or any combination thereof. For example, "including at least one of the following: A, B, C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Similarly, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0026] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0027] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0028] It should be noted that step designations such as S1 and S2 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the protection scope of this application.

[0029] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0030] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0031] Smart terminals can be implemented in various forms. For example, the smart terminals described in this application may include smart terminals such as mobile phones, tablets, laptops, handheld computers, personal digital assistants (PDAs), portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, etc., as well as fixed terminals such as digital TVs and desktop computers.

[0032] The following description will use a mobile terminal as an example. Those skilled in the art will understand that, apart from elements specifically designed for mobile purposes, the construction according to the embodiments of this application can also be applied to fixed-type terminals.

[0033] Please see Figure 1 This is a schematic diagram of the hardware structure of a mobile terminal implementing various embodiments of this application. The mobile terminal 100 may include: an RF (Radio Frequency) unit 101, a WiFi module 102, an audio output unit 103, an A / V (Audio / Video) input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, a processor 110, and a power supply 111, etc. Those skilled in the art will understand that... Figure 1 The mobile terminal structure shown does not constitute a limitation on the mobile terminal. The mobile terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0034] The following is combined with Figure 1 A detailed introduction to each component of the mobile terminal: The radio frequency unit 101 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with the processor 110; additionally, it transmits uplink data to the base station. Typically, the radio frequency unit 101 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier, and a duplexer. Furthermore, the radio frequency unit 101 can also communicate wirelessly with networks and other devices. The aforementioned wireless communications may use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000 (Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), FDD-LTE (Frequency Division Duplexing-Long Term Evolution), TDD-LTE (Time Division Duplexing-Long Term Evolution), 5G, and 6G.

[0035] WiFi is a short-range wireless transmission technology. Mobile terminals, through the WiFi module 102, can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 1 WiFi module 102 is shown, but it is understood that it is not a necessary component of a mobile terminal and can be omitted as needed without changing the nature of the invention.

[0036] The audio output unit 103 can convert audio data received by the radio frequency unit 101 or the WiFi module 102 or stored in the memory 109 into audio signals and output them as sound when the mobile terminal 100 is in call signal receiving mode, call mode, recording mode, voice recognition mode, broadcast receiving mode, etc. Furthermore, the audio output unit 103 can also provide audio output related to specific functions performed by the mobile terminal 100 (e.g., call signal receiving sound, message receiving sound, etc.). The audio output unit 103 may include a speaker, a buzzer, etc.

[0037] The A / V input unit 104 is used to receive audio or video signals. The A / V input unit 104 may include a graphics processing unit (GPU) 1041 and a microphone 1042. The GPU 1041 processes image data of still images or videos acquired by an image capture device (such as a camera) in video capture mode or image capture mode. The processed image frames can be displayed on the display unit 106. The image frames processed by the GPU 1041 can be stored in the memory 109 (or other storage media) or transmitted via the radio frequency unit 101 or the WiFi module 102. The microphone 1042 can receive sound (audio data) in operating modes such as telephone call mode, recording mode, and voice recognition mode, and can process such sound into audio data. The processed audio (voice) data can be converted into a format that can be transmitted to a mobile communication base station via the radio frequency unit 101 in telephone call mode. The microphone 1042 can implement various types of noise cancellation (or suppression) algorithms to eliminate (or suppress) noise or interference generated during the reception and transmission of audio signals.

[0038] The mobile terminal 100 also includes at least one sensor 105, such as a light sensor, a motion sensor, and other sensors. Optionally, the light sensor includes an ambient light sensor and a proximity sensor. Optionally, the ambient light sensor can adjust the brightness of the display panel 1061 according to the ambient light level, and the proximity sensor can turn off the display panel 1061 and / or backlight when the mobile terminal 100 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc. Other sensors that may be configured in the phone, such as fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0039] The display unit 106 is used to display information input by the user or information provided to the user. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0040] User input unit 107 can be used to receive input numerical or character information, and generate key signal inputs related to user settings and function control of the mobile terminal. Optionally, user input unit 107 may include touch panel 1071 and other input devices 1072. Touch panel 1071, also known as touch screen, can collect touch operations on or near the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near touch panel 1071), and drive corresponding connection devices according to a pre-set program. Touch panel 1071 may include two parts: a touch detection device and a touch controller. Optionally, the touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to processor 110, and can receive and execute commands sent by processor 110. In addition, touch panel 1071 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1071, the user input unit 107 may also include other input devices 1072. Optionally, other input devices 1072 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc., without being specifically limited here.

[0041] Optionally, the touch panel 1071 may cover the display panel 1061. When the touch panel 1071 detects a touch operation on or near it, it transmits the information to the processor 110 to determine the type of touch event. Subsequently, the processor 110 provides corresponding visual output on the display panel 1061 based on the type of touch event. Although in Figure 1 In this embodiment, the touch panel 1071 and the display panel 1061 are two independent components to realize the input and output functions of the mobile terminal. However, in some embodiments, the touch panel 1071 and the display panel 1061 can be integrated to realize the input and output functions of the mobile terminal. The specific implementation is not limited here.

[0042] Interface unit 108 serves as an interface through which at least one external device can connect to mobile terminal 100. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 108 may be used to receive input (e.g., data, power, etc.) from the external device and transmit the received input to one or more elements within mobile terminal 100, or it may be used to transmit data between mobile terminal 100 and the external device.

[0043] The memory 109 can be used to store software programs and various data. The memory 109 may primarily include a program storage area and a data storage area. Optionally, the program storage area may store the operating system, applications required for at least one function (such as sound playback, image playback, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory 109 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0044] The processor 110 is the control center of the mobile terminal. It connects various parts of the mobile terminal via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 109, and by calling data stored in the memory 109, it performs various functions and processes data of the mobile terminal, thereby providing overall monitoring of the mobile terminal. The processor 110 may include one or more processing units; preferably, the processor 110 may integrate an application processor and a modem processor. Optionally, the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 110.

[0045] The mobile terminal 100 may also include a power supply 111 (such as a battery) that supplies power to various components. Preferably, the power supply 111 can be logically connected to the processor 110 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0046] although Figure 1 As not shown, the mobile terminal 100 may also include a Bluetooth module, etc., which will not be described in detail here.

[0047] To facilitate understanding of the embodiments of this application, the communication network system on which the mobile terminal of this application is based is described below.

[0048] Please see Figure 2 , Figure 2 This application provides a communication network system architecture diagram. The communication network system is an LTE system based on the universal mobile communication technology. The LTE system includes a UE (User Equipment) 201, an E-UTRAN (Evolved UMTS Terrestrial Radio Access Network) 202, an EPC (Evolved Packet Core) 203, and the operator's IP services 204, which are connected in sequence.

[0049] Optionally, UE201 can be the aforementioned terminal 100, which will not be described in detail here.

[0050] E-UTRAN202 includes eNodeB2021 and other eNodeB2022s. Optionally, eNodeB2021 can connect to other eNodeB2022s via backhaul (e.g., X2 interface). eNodeB2021 connects to EPC203 and can provide UE201 with access to EPC203.

[0051] EPC203 may include an MME (Mobility Management Entity) 2031, an HSS (Home Subscriber Server) 2032, other MMEs 2033, an SGW (Serving Gateway) 2034, a PGW (Packet Data Network Gateway) 2035, and a PCRF (Policy and Charging Rules Function) 2036, etc. Optionally, MME2031 is the control node that handles signaling between UE201 and EPC203, providing bearer and connection management. HSS2032 is used to provide registers to manage functions such as the Home Location Register (not shown in the figure) and stores user-specific information such as service characteristics and data rates. All user data can be sent through SGW2034. PGW2035 can provide UE 201 IP address allocation and other functions. PCRF2036 is the policy and charging control decision point for service data flow and IP bearer resources. It selects and provides available policy and charging control decisions for the policy and charging enforcement function unit (not shown in the figure).

[0052] IP services 204 may include the Internet, intranet, IMS (IP Multimedia Subsystem), or other IP services.

[0053] Although the above description uses the LTE system as an example, those skilled in the art should know that this application is not only applicable to the LTE system, but also to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA, 5G and future new network systems (such as 6G), etc., without limitation.

[0054] Based on the above-described mobile terminal hardware structure and communication network system, various embodiments of this application are proposed.

[0055] First Embodiment Reference Figure 3 , Figure 3 This is a flowchart illustrating a voice processing method according to the first embodiment. The voice processing method of this application embodiment can be applied to a smart terminal (such as a mobile phone) and includes the following steps (e.g., steps S1 to S2): S1: Determine the corresponding translation processing strategy based on the obtained speaking scenario.

[0056] Optionally, the speaking context can characterize the background of the speaking event determined by at least one of three factors: a specific environment, participating roles, and the purpose of speaking. Examples of speaking contexts include meeting scenarios, teaching scenarios, negotiation scenarios, interview scenarios, and medical scenarios.

[0057] Optionally, the methods for obtaining the speaking scenario include, but are not limited to, at least one of the following: The speaking scenario is obtained based on the received setting instructions; The speaking scenario is obtained based on at least one of the speech features corresponding to the speech to be processed, transaction arrangement information, and environmental perception data. Voice features include at least one of the following: number of speakers, keywords, content text, and dialogue structure.

[0058] Optionally, the speech features can represent any feature extracted from speech that supports speech scene recognition. Optionally, the speech features include, but are not limited to, at least one of the following: number of speakers, keywords, content text, and dialogue structure, and may also include other features that support speech scene recognition.

[0059] Optionally, the number of speakers is an auxiliary feature for speech scene recognition. The number of speakers provides preliminary contextual information for speech scene recognition, helping to narrow down the possible speech scenes. For example, conference scenes typically have more speakers, while teaching scenes have fewer. The number of speakers can be combined with other speech features (such as keywords, dialogue structure, and text content), environmental awareness data (such as environmental images and videos), and event scheduling information (such as daily schedules and meeting schedules) to improve the accuracy of speech scene recognition. For example, a large number of speakers with technical terms (i.e., keywords) and a turn-taking structure (i.e., dialogue structure) suggests a conference scene; conversely, a small number of speakers with medical-related keywords and a question-and-answer format (i.e., dialogue structure) suggests a medical scene.

[0060] Optionally, keywords provide semantic information for identifying speaking scenarios, helping to narrow down the range of possible speaking scenarios.

[0061] Optionally, the content text can represent the text describing the content of the speech obtained by recognizing the speech to be processed.

[0062] Optionally, the content text makes it easier to accurately extract keywords, semantic logic, and / or situational structure corresponding to scene recognition. For example, keywords in the content text such as "summary," "symptoms," and "topic" can initially point to different scenarios such as meetings, medical treatment, and teaching. Then, analyzing the semantic logic and sentence structure of the content text, such as task allocation sentences in meetings, consultation sentences in medical treatment, and explanation sentences in teaching, can further support the recognition of speaking scenarios. The content text can be combined with other speech features (such as dialogue structure, number of speakers, etc.), environmental awareness data (such as environmental images, environmental videos, etc.), and event arrangement information (such as daily schedule information, meeting schedule information, etc.) to improve the accuracy of speaking scenario recognition.

[0063] Optionally, the dialogue structure represents the logical organization and interaction pattern of the dialogue in the speech to be processed, which is determined by at least one of the following: statement order, participant roles, semantic association, and tone.

[0064] Optionally, different speaking scenarios have specific dialogue structures. For example, the dialogue structure in a meeting scenario is more formal in tone and sentence order, with clear turn-taking. In another example, the dialogue structure in a medical scenario, including a consultation scenario, presents a consultation-response pattern.

[0065] Optionally, the dialogue structure can be used as one of the features for speech scene recognition. It can be combined with other speech features (such as the number of speakers, keywords, content text, etc.), environmental perception data (such as environmental images, environmental videos, etc.) and event arrangement information (such as schedule information, meeting arrangement information, etc.) to improve the accuracy of speech scene recognition.

[0066] Optionally, it can acquire speech features that support speech scene recognition, such as opening remarks or speech recorded for a preset duration. Optionally, while recording speech for a preset duration, the initial speech recorded within the preset duration can be translated to obtain an initial translation result. After completing the speech recording for the preset duration and obtaining speech features that support speech scene recognition, the initial translation result can be optimized based on the subsequently confirmed speech scene and its corresponding translation processing strategy to obtain a translation result that matches the context of the speech scene. Furthermore, for speech features received after confirming the speech scene, the translation processing strategy corresponding to the speech scene can be directly applied for translation processing until the speech event corresponding to the speech scene ends. In this way, all translation results obtained under the speech event can match the actual context.

[0067] Optionally, event scheduling information can provide key clues for identifying speaking scenarios. By analyzing details such as time, location, participants, and activity content, and / or their corresponding event attributes, the type of speaking scenario can be inferred. For example, if meeting scheduling information obtained from a meeting application or calendar application shows "A product launch will be held in the conference room at 3 PM today, with participants including company executives and media representatives," it can be inferred to be a meeting scenario; similarly, if calendar scheduling information obtained from a calendar application shows "Visiting a hospital at 8 AM today," it can be inferred to be a medical scenario or a visit to a doctor.

[0068] Optionally, the transaction arrangement information can directly identify the speaking scenario, or it can be combined with other information (such as voice features, environmental perception data, etc.) for comprehensive processing to identify the speaking scenario, so as to realize the identification of the speaking scenario through multi-dimensional information, thereby improving the accuracy and efficiency of scenario identification.

[0069] Optionally, the voice processing method provided in this embodiment can be embodied in a smart terminal as a voice processing function or voice processing application, which can be integrated or associated with a calendar application and / or a meeting application, thereby facilitating the acquisition of event arrangement information in the calendar application and / or the meeting application; in addition, in the calendar application and / or the meeting application, the voice processing function or voice processing application can be directly or indirectly invoked to perform translation processing work at the start of the event or meeting. In this way, the voice processing function or voice processing application combined with the calendar application and / or the meeting application can provide context extension services to each other.

[0070] Optionally, environmental perception data can characterize any data that reflects the real-world environment acquired through various sensors and / or applications. Environmental perception data includes, but is not limited to, visual perception data (e.g., images of the real-world environment captured by a camera, videos of the real-world environment, etc.), spatial environment data (e.g., location, time, etc.), and the status of connected devices (e.g., the status of a specific microphone, the status of a specific audio playback device, etc.).

[0071] Optionally, environmental perception data can directly identify the speaking scenario based on the real environment it reflects. It can also be combined with other information (such as voice features, event arrangement information, etc.) for comprehensive processing to identify the speaking scenario, so as to realize the identification of the speaking scenario through multi-dimensional information, thereby improving the accuracy and efficiency of scenario recognition.

[0072] Optionally, the speech scene acquisition can be based on information of a single modality / dimensional or information of a single modality / dimensional (e.g., speech, text, image, etc.) and preset information-scene association information, and / or it can be based on information of a single modality / dimensional or information of a single modality / dimensional (e.g., speech, text, image, etc.) and a pre-built scene recognition model.

[0073] Optionally, the speaking scenario can be obtained directly based on the received setting instructions. For example, the user can trigger a setting instruction through a setting operation to directly set the speaking scenario.

[0074] Optionally, the speaking scenario can also be obtained by predicting and displaying one or more speaking scenarios based on at least one of the voice features corresponding to the voice to be processed, transaction arrangement information, and environmental perception data, so as to determine a speaking scenario that meets the user's needs based on the triggered setting instructions.

[0075] Optionally, the translation processing strategy can characterize the specific process or rules for translating speech and / or performing other translation-related processing based on the characteristics or information associated with the speaking context.

[0076] Optionally, the translation processing strategy may include a content translation strategy corresponding to the speaking scenario and / or a translation result processing strategy corresponding to the speaking scenario.

[0077] Optionally, the content translation strategy can characterize the specific process or rules for content translation processing of speech based on the characteristics or information associated with the speaking context.

[0078] Optionally, the translation result processing strategy can characterize the specific process or rules for applying and processing the translation results based on the characteristics or information associated with the speaking scenario.

[0079] Optionally, step S1 may include: determining the translation processing strategy corresponding to the speech scenario based on the obtained speech scenario and scenario-strategy correspondence information. Optionally, the scenario-strategy correspondence information can represent information that associates various speech scenarios with various translation processing strategies one-to-one. In this way, the technical solution of this application can match different translation processing strategies according to different identified speech scenarios, making the obtained translation results more consistent with the actual context and avoiding or reducing translation deviations.

[0080] S2: Perform the corresponding translation processing work on the speech to be processed according to the translation processing strategy.

[0081] The speech processing method provided in this embodiment can be applied to smart terminals, including the following steps: S1: Determine the corresponding translation processing strategy based on the obtained speech scenario; S2: Perform the corresponding translation processing work on the speech to be processed according to the translation processing strategy.

[0082] The technical solution of this embodiment can identify the speaking scenario and configure a corresponding target translation processing strategy according to the speaking scenario. By using a target translation processing strategy adapted to the speaking scenario to translate the speech, the resulting translation is more in line with the actual context, avoiding or reducing translation errors. This makes the translation result more consistent with the user's expression logic and habits in a specific scenario, thus enhancing the user experience. Therefore, the technical solution of this embodiment provides a speech translation function with speaking scenario awareness, solving the problem of traditional speech translation methods lacking awareness of speaking scenarios, resulting in translation results that do not match the context, thereby improving the user experience.

[0083] Second Embodiment Based on the first embodiment described above, a second embodiment of this application is proposed. (Refer to...) Figure 4 , Figure 4 This is a flowchart illustrating a voice processing method according to the second embodiment. The voice processing method of this application embodiment can be applied to a smart terminal (such as a mobile phone) and includes the following steps: S21: Determine the corresponding content translation strategy and translation result processing strategy based on the obtained speaking scenario.

[0084] Optionally, the speaking context can characterize the background of the speaking event determined by at least one of three factors: a specific environment, participating roles, and the purpose of speaking. Examples of speaking contexts include meeting scenarios, teaching scenarios, negotiation scenarios, interview scenarios, and medical scenarios.

[0085] Optionally, the methods for obtaining the speaking scenario include, but are not limited to, at least one of the following: The speaking scenario is obtained based on the received setting instructions; The speaking scenario is obtained based on at least one of the speech features corresponding to the speech to be processed, transaction arrangement information, and environmental perception data. Voice features include at least one of the following: number of speakers, keywords, content text, and dialogue structure.

[0086] Optionally, the speech features can represent any feature extracted from speech that supports speech scene recognition. Optionally, the speech features include, but are not limited to, at least one of the following: number of speakers, keywords, content text, and dialogue structure, and may also include other features that support speech scene recognition.

[0087] Optionally, the number of speakers is an auxiliary feature for speech scene recognition. The number of speakers provides preliminary contextual information for speech scene recognition, helping to narrow down the possible speech scenes. For example, conference scenes typically have more speakers, while teaching scenes have fewer. The number of speakers can be combined with other speech features (such as keywords, dialogue structure, and text content), environmental awareness data (such as environmental images and videos), and event scheduling information (such as daily schedules and meeting schedules) to improve the accuracy of speech scene recognition. For example, a large number of speakers with technical terms (i.e., keywords) and a turn-taking structure (i.e., dialogue structure) suggests a conference scene; conversely, a small number of speakers with medical-related keywords and a question-and-answer format (i.e., dialogue structure) suggests a medical scene.

[0088] Optionally, keywords provide semantic information for identifying speaking scenarios, helping to narrow down the range of possible speaking scenarios.

[0089] Optionally, the content text can represent the text describing the content of the speech obtained by recognizing the speech to be processed.

[0090] Optionally, the content text makes it easier to accurately extract keywords, semantic logic, and / or situational structure corresponding to scene recognition. For example, keywords in the content text such as "summary," "symptoms," and "topic" can initially point to different scenarios such as meetings, medical treatment, and teaching. Then, analyzing the semantic logic and sentence structure of the content text, such as task allocation sentences in meetings, consultation sentences in medical treatment, and explanation sentences in teaching, can further support the recognition of speaking scenarios. The content text can be combined with other speech features (such as dialogue structure, number of speakers, etc.), environmental awareness data (such as environmental images, environmental videos, etc.), and event arrangement information (such as daily schedule information, meeting schedule information, etc.) to improve the accuracy of speaking scenario recognition.

[0091] Optionally, the dialogue structure represents the logical organization and interaction pattern of the dialogue in the speech to be processed, which is determined by at least one of the following: statement order, participant roles, semantic association, and tone.

[0092] Optionally, different speaking scenarios have specific dialogue structures. For example, the dialogue structure in a meeting scenario is more formal in tone and sentence order, with clear turn-taking. In another example, the dialogue structure in a medical scenario, including a consultation scenario, presents a consultation-response pattern.

[0093] Optionally, the dialogue structure can be used as one of the features for speech scene recognition. It can be combined with other speech features (such as the number of speakers, keywords, content text, etc.), environmental perception data (such as environmental images, environmental videos, etc.) and event arrangement information (such as schedule information, meeting arrangement information, etc.) to improve the accuracy of speech scene recognition.

[0094] Optionally, it can acquire speech features that support speech scene recognition, such as opening remarks or speech recorded for a preset duration. Optionally, while recording speech for a preset duration, the initial speech recorded within the preset duration can be translated to obtain an initial translation result. After completing the speech recording for the preset duration and obtaining speech features that support speech scene recognition, the initial translation result can be optimized based on the subsequently confirmed speech scene and its corresponding translation processing strategy to obtain a translation result that matches the context of the speech scene. Furthermore, for speech features received after confirming the speech scene, the translation processing strategy corresponding to the speech scene can be directly applied for translation processing until the speech event corresponding to the speech scene ends. In this way, all translation results obtained under the speech event can match the actual context.

[0095] Optionally, event scheduling information can provide key clues for identifying speaking scenarios. By analyzing details such as time, location, participants, and activity content, and / or their corresponding event attributes, the type of speaking scenario can be inferred. For example, if meeting scheduling information obtained from a meeting application or calendar application shows "A product launch will be held in the conference room at 3 PM today, with participants including company executives and media representatives," it can be inferred to be a meeting scenario; similarly, if calendar scheduling information obtained from a calendar application shows "Visiting a hospital at 8 AM today," it can be inferred to be a medical scenario or a visit to a doctor.

[0096] Optionally, the transaction arrangement information can directly identify the speaking scenario, or it can be combined with other information (such as voice features, environmental perception data, etc.) for comprehensive processing to identify the speaking scenario, so as to realize the identification of the speaking scenario through multi-dimensional information, thereby improving the accuracy and efficiency of scenario identification.

[0097] Optionally, the voice processing method provided in this embodiment can be embodied in a smart terminal as a voice processing function or voice processing application, which can be integrated or associated with a calendar application and / or a meeting application, thereby facilitating the acquisition of event arrangement information in the calendar application and / or the meeting application; in addition, in the calendar application and / or the meeting application, the voice processing function or voice processing application can be directly or indirectly invoked to perform translation processing work at the start of the event or meeting. In this way, the voice processing function or voice processing application combined with the calendar application and / or the meeting application can provide context extension services to each other.

[0098] Optionally, environmental perception data can characterize any data that reflects the real-world environment acquired through various sensors and / or applications. Environmental perception data includes, but is not limited to, visual perception data (e.g., images of the real-world environment captured by a camera, videos of the real-world environment, etc.), spatial environment data (e.g., location, time, etc.), and the status of connected devices (e.g., the status of a specific microphone, the status of a specific audio playback device, etc.).

[0099] Optionally, environmental perception data can directly identify the speaking scenario based on the real environment it reflects. It can also be combined with other information (such as voice features, event arrangement information, etc.) for comprehensive processing to identify the speaking scenario, so as to realize the identification of the speaking scenario through multi-dimensional information, thereby improving the accuracy and efficiency of scenario recognition.

[0100] Optionally, the speech scene acquisition can be based on information of a single modality / dimensional or information of a single modality / dimensional (e.g., speech, text, image, etc.) and preset information-scene association information, and / or it can be based on information of a single modality / dimensional or information of a single modality / dimensional (e.g., speech, text, image, etc.) and a pre-built scene recognition model.

[0101] Optionally, the speaking scenario can be obtained directly based on the received setting instructions. For example, the user can trigger a setting instruction through a setting operation to directly set the speaking scenario.

[0102] Optionally, the speaking scenario can also be obtained by predicting and displaying one or more speaking scenarios based on at least one of the voice features corresponding to the voice to be processed, transaction arrangement information, and environmental perception data, so as to determine a speaking scenario that meets the user's needs based on the triggered setting instructions.

[0103] S22: Perform content translation processing on the speech to be processed according to the content translation strategy corresponding to the speaking scenario to obtain the translation result.

[0104] Optionally, the content translation strategy can characterize the specific process or rules for content translation processing of speech based on the characteristics or information associated with the speaking context.

[0105] Optionally, content translation strategies include, but are not limited to, at least one of the following: Obtain a basic terminology database corresponding to the speaking scenario; Obtain contextual knowledge information corresponding to the speaking scenario; Associate the basic terminology database with the custom terminology database to obtain terminology database association information; Based on contextual knowledge, a basic terminology database, and / or related terminology database information, the speech to be processed is translated to obtain the translation result.

[0106] Optionally, the basic terminology database is customized for a specific speaking scenario, containing a resource collection of commonly used words and phrases in that specific speaking scenario, along with their translations in one or more languages. Optionally, the basic terminology database may cover the core keywords of the specific speaking scenario. Optionally, the basic terminology database may also include or be associated with contextual information such as parts of speech, phrase collocations, and semantic relationships to adapt to the contextual needs of the specific speaking scenario.

[0107] Optionally, the contextual knowledge information corresponding to the speaking scenario can be represented as a "knowledge map" for a specific speaking scenario. This map presents the key terms, concepts, and their interrelationships within the specific speaking scenario in a graphical form. For example, in a teaching scenario, it can include nodes such as "question" and "knowledge point," and mark the explanation of the "knowledge point" that the "question" may trigger. For instance, when translating a sentence like "How to understand the square root of a negative number?", the model can use the graph to identify that "negative number" and "square root" belong to mathematical knowledge nodes, and then choose a more accurate and context-appropriate translation, such as "how to comprehend the square root of a negative number from a mathematical perspective?", rather than a simple literal translation. This not only improves the accuracy of the translation but also makes the translation more in line with the expression habits of the target language.

[0108] Optionally, the terminology association information obtained by associating the basic terminology database with the custom terminology database can support merging the basic terminology database and one or more custom terminology databases or dynamically switching between the basic terminology database and at least one auto-terminal terminology database during content translation processing. This allows the translation results obtained from content translation processing to not only adapt to the context corresponding to a specific speaking scenario, but also meet the user's personalized needs and / or the need for accurate translation of additional topic content.

[0109] Optionally, the terminology database association information can also be associated with or include terminology database priority information. Thus, when a specific word in the speech to be processed corresponds to different translation content in different terminology databases, the translation content corresponding to the specific word in the terminology database with the highest priority can be used as the component of the generated translation result based on the terminology database priority information.

[0110] Optionally, in the content translation strategy of this embodiment, when the speech to be processed is translated only based on the basic terminology database corresponding to the speaking scenario to obtain the translation result, the obtained translation result can be more in line with the actual context, avoiding or reducing translation deviation.

[0111] Optionally, in the content translation strategy of this embodiment, when translating the speech to be processed based on contextual knowledge information and a basic terminology database to obtain translation results, the contextual knowledge information, as a "knowledge map" of a specific speaking scenario, can help the model understand the deeper meaning and interrelationships of words and sentences in a specific speaking scenario, thereby avoiding semantic deviations caused by simple literal translation. Furthermore, the basic terminology database ensures the accurate translation of key terms. The combination of the two ensures that the translation results not only accurately convey the original meaning but also conform to the expression habits of the target language, effectively reducing translation errors caused by contextual differences. Therefore, it can significantly improve the accuracy and contextual fit of the translation results.

[0112] Optionally, in the content translation strategy of this embodiment, when translating the speech to be processed based on contextual knowledge information and terminology database association information to obtain translation results, the basic terminology database corresponding to the speaking scenario will be called during the translation process to enhance the adaptability of the context. Moreover, when specific words in the speech to be processed have different translation contents in the basic terminology database and the custom terminology database, the translation contents in the custom terminology database can be used to a limited extent to meet the actual needs of the user. In this way, the technical solution of this embodiment can adapt to the context of a specific speaking scenario and dynamically switch different terminology databases to meet the user's personalized needs or other needs during the translation process. As a result, the final translation result not only adapts to the context of a specific speaking scenario to ensure the accurate translation of professional vocabulary / or terms, but also meets the user's needs and enhances the user experience.

[0113] Optionally, in the content translation strategy of this embodiment, when translating the speech to be processed based on contextual knowledge information and terminology database association information to obtain translation results, it can further ensure that the translation results closely match the professional context of the specific speaking scenario, ensure the accuracy of key term translation, and enable dynamic switching of terminology database to meet the user's personalized needs or other needs, thereby further enhancing the user experience.

[0114] Optionally, the translation processing in this embodiment can be performed by a pre-built translation model. After receiving the speech to be processed, the translation model can call contextual knowledge information, basic terminology database and / or terminology database association information to perform translation processing and obtain translation results.

[0115] Optionally, the method of obtaining the custom terminology database includes at least one of the following: Identify the target users corresponding to the speaking scenarios, and use the personalized terminology library associated with the target users as the custom terminology library; Identify additional topics and use the professional terminology database corresponding to the additional topics as a custom terminology database.

[0116] Optionally, a personalized terminology database can be a terminology database obtained after the user has pre-configured it, which can cover the user's custom vocabulary / terms and their corresponding popular translations.

[0117] Optionally, the personalized terminology database can be associated with a specific user's user information and stored locally or on a server.

[0118] Optionally, the technical solution of this embodiment can obtain one or more target users in the speaking scenario through biometric recognition technology and / or user information selection operation. This allows the personalized terminology library of the target user to be called from the local machine or server as a custom terminology library. During translation processing, voiceprint recognition can be performed on the speech to be processed to identify the target user. Based on the basic terminology library and the target user's personalized terminology library, the corresponding speech segment of the target user in the speech to be processed is translated. Thus, the technical solution of this embodiment not only ensures that the translation result closely matches the professional context of the specific speaking scenario and ensures the accuracy of key terminology translation, but also enables dynamic switching of terminology libraries to meet the personalized needs or other requirements of one or more users, thereby further enhancing the user experience.

[0119] Optionally, the technical solution of this embodiment can use speech recognition technology to identify topic keywords in the speech to be processed to determine additional topics in a specific speaking scenario, and / or receive a topic selection operation to set additional topics, thereby determining a professional terminology database corresponding to the additional topics as a custom terminology database. In this way, the technical solution of this embodiment not only ensures that the translation results closely match the professional context of a specific speaking scenario, but also dynamically switches terminology databases to meet users' diverse topic communication needs and accurate translation requirements, thereby further enhancing the user experience.

[0120] S23: Apply the translation results to the translation result processing strategy corresponding to the speaking scenario.

[0121] Optionally, the translation result processing strategy can characterize the specific process or rules for applying and processing the translation results based on the characteristics or information associated with the speaking scenario.

[0122] Optionally, the translation result processing strategy includes, but is not limited to, at least one of the following: The translation results are displayed according to a target display strategy that matches the speaking context. Obtain the event record file based on the event record template corresponding to the speaking scenario and the translation results.

[0123] Optionally, the target display strategy can characterize the specific way or process of displaying the translation results in one or more modalities.

[0124] Optionally, the target display strategy includes at least one of the following: Display the text information corresponding to the translation result according to the target screen display mode corresponding to the speaking scenario; Play the translated audio corresponding to the translation result.

[0125] Optionally, the target screen display mode corresponding to the speaking scenario can characterize the effect style of displaying the text information corresponding to the translation result on the display device.

[0126] Optionally, the target screen display mode includes, but is not limited to, at least one of the following: split-screen display mode, scrolling text mode, and prompt card mode.

[0127] Optionally, the content translation processing may further include speaker differentiation based on the speech to be processed, thereby obtaining the corresponding content text and / or translated content for each speaker, so that the translation result can support the display of the translated content corresponding to each speaker. Thus, the technical solution of this embodiment can distinguish and display the text information corresponding to the translated content of each speaker.

[0128] Optionally, the technical solution of this embodiment can play the translated audio corresponding to the translation result through a speaker or headphones.

[0129] For example, in a business negotiation scenario, the target display strategy is to display the text information corresponding to the translation result, and the target screen display mode for the business negotiation scenario is a split-screen display mode. Therefore, the dialogue text corresponding to the speech to be processed and the text information corresponding to the translation result can be displayed side-by-side on the display device. In a teaching scenario, the target display strategy is to display the text information corresponding to the translation result and play the translated speech corresponding to the translation result. The target display mode for the teaching scenario is a scrolling subtitle mode. Therefore, the content text corresponding to the speech to be processed and the translation result can be displayed on the display device in the form of bilingual scrolling subtitles, and the associated student terminal or student's headphones can be controlled to synchronously play the translated speech corresponding to the translation result. In an interview scenario, the target display strategy is to display the text information corresponding to the translation result and play the translated speech corresponding to the translation result. The target display mode for the interview scenario is a prompt card mode. Therefore, the full text or key phrases of the translation result corresponding to the speech to be processed can be concisely and in real-time displayed on the prompt card on the screen, and the translated speech corresponding to the translation result can be played through the associated audio playback device.

[0130] Optionally, the technical solution of this embodiment can match one or more modalities (such as text, images, and audio) to different speaking scenarios to support the display of translation results. Furthermore, when displaying text through a display device, different screen display strategies can be matched to different speaking scenarios so that the display of translation results meets the environmental characteristics and user needs of each speaking scenario.

[0131] Optionally, the event record template can represent and record important matters determined based on all or part of the translation results in a specific speaking scenario. For example, the event record template for a meeting scenario is a meeting minutes template that records key summaries and / or pending tasks; the event record template for a teaching scenario is a class minutes template; and the event record template for a business negotiation scenario is a template for recording matters according to negotiation rounds.

[0132] Optionally, obtaining the event record file based on the event record template and translation results corresponding to the speaking scenario may include: in response to meeting preset conditions, obtaining the event record file based on the event record template and translation results corresponding to the speaking scenario.

[0133] Optionally, the preset conditions can represent any condition that indicates the core speech in a specific speaking scenario has ended and / or any condition that indicates the user has left the speaking environment (or is absent) in the speaking scenario. Thus, the technical solution of this embodiment can, when determining that the core speech in a specific speaking scenario has ended and / or determining that the user has left the speaking environment (e.g., answering a phone call or leaving the environment where the smart terminal is located), obtain a task record file based on the task record template and translation results corresponding to the specific speaking scenario to complete the recording and summarization of important tasks and / or pending tasks (task arrangement information).

[0134] Optionally, the preset conditions include at least one of the following: The duration for which no new voice messages have been received exceeds the preset duration; The process ends when the speech recognition process reaches the point of being spoken. Application switching operation detected; Preset command received.

[0135] Optionally, the speech process is considered to be the end process based on the speech recognition process to be processed. For example, the speech recognition process is considered to be the end process based on the preset keywords corresponding to the end process. Alternatively, the speech recognition process is considered to be the end process based on the keywords of the speech content not matching the terms in the terminology library corresponding to the current speech scenario, and / or the number of mismatches exceeds a preset number.

[0136] Optionally, the speech processing method provided in this embodiment also includes, but is not limited to, at least one of the following: Obtain transaction arrangement information from the transaction log file; Display transaction arrangement information; The target application is determined based on the transaction attributes and preset association information corresponding to the transaction arrangement information, and the target application is controlled to record or process the transaction arrangement information.

[0137] Optionally, the preset association information can characterize the relationship between transaction attributes and applications.

[0138] Optionally, transaction attributes can define the categories of transaction scheduling information.

[0139] For example, the preset associated information includes: if the transaction attribute is a meeting arrangement class, the corresponding application is a meeting application, an email application, or a calendar application; if the transaction attribute is a calendar arrangement class, the corresponding application is a calendar application.

[0140] Optionally, the corresponding target application can be determined based on the transaction attributes and preset association information corresponding to the transaction arrangement information, and the target application can be controlled to record or process the transaction arrangement information. For example, if the target application is determined to be a meeting application, an email application, or a calendar application based on the meeting arrangement information, then the meeting application can be controlled to process meeting reservations based on the meeting arrangement information, the calendar application can be controlled to record the meeting arrangement information, and the email application can be controlled to edit notification emails and / or automatically send notification emails to relevant persons based on the meeting arrangement information. Similarly, if the target application is determined to be a calendar application based on the calendar arrangement information, then the calendar application can be controlled to record the calendar arrangement information. In this way, the technical solution of this embodiment can be associated with or integrated with other applications to provide context extension services.

[0141] Optionally, the speech processing method provided in this embodiment may further include: displaying the text information corresponding to the translation result, recording the modification information of the text information; determining the target translation text whose modification count exceeds a preset number based on the modification information; and updating the terminology database corresponding to the content translation processing based on the target translation text and its corresponding modification result. Thus, the technical solution of this embodiment can provide a terminology learning and error correction mechanism, continuously optimizing the translation effect in specific speaking scenarios.

[0142] Optionally, the speech processing method provided in this embodiment may further include at least one of the following: Sentiment analysis and tone recognition are performed based on the content to be processed and / or the translation results to determine the target wording and / or target sentence corresponding to the preset emotion in the translation results; when displaying the text information corresponding to the translation results, the target wording and / or target sentence are highlighted; Identify prohibited words based on the content to be processed and / or the translation results to determine the prohibited words in the translation results; highlight the prohibited words when displaying the text information corresponding to the translation results; Upon receiving a modification request for the highlighted content, update the translation result and display the corresponding text information of the updated translation result.

[0143] Optionally, preset emotions such as happiness, seriousness, and anger can be used.

[0144] Optionally, preset tones such as command or rhetorical question can be used.

[0145] Thus, the technical solution of this embodiment can conveniently determine the content to be optimized in the translation result through at least one of the following content recognition methods: emotion analysis, tone recognition, and violation word recognition. This helps users adjust the tone and wording of the translation so that the translation result meets the user's needs.

[0146] Optionally, the specific implementation and beneficial effects of the speech processing method provided in this embodiment can be referenced or arbitrarily combined with each other without contradicting the technical solution of the first embodiment, and will not be elaborated here.

[0147] The speech processing method provided in this embodiment can be applied to smart terminals, including the following steps: S21: Determine the corresponding content translation strategy and translation result processing strategy based on the acquired speech scenario; S22: Perform content translation processing on the speech to be processed according to the content translation strategy corresponding to the speech scenario to obtain the translation result; S23: Apply the translation result to the speech scenario according to the translation result processing strategy corresponding to the speech scenario. Thus, the technical solution of this embodiment can perform content translation processing on the speech to be processed using a specific content translation strategy adapted to the speech scenario, making the obtained translation result more consistent with the actual context, avoiding or reducing translation deviations, thereby making the translation result more in line with the user's expression logic and habits in a specific scenario, and enhancing the user experience; the technical solution of this embodiment can also apply or reprocess the translation result using a specific translation result processing strategy adapted to the speech scenario to meet the user's usage or processing habits of the translation result in a specific scenario, further enhancing the user experience.

[0148] Furthermore, the technical solution of this embodiment supports a custom terminology database when performing content translation processing. This allows the translation results obtained from the content translation processing to not only adapt to the context corresponding to a specific speaking scenario, but also meet the user's personalized needs and / or the need for accurate translation of additional topic content, thereby enhancing the application value of the translation results obtained in various speaking scenarios.

[0149] The technical solution of this embodiment also provides multimodal interaction methods (such as a combination of screen display and audio playback), improving user experience and speaking efficiency. The technical solution of this embodiment also supports key information recording, speaker identification, and contextual extension services, enabling the voice translation function implemented in this embodiment to possess a high level of intelligence.

[0150] This application also provides a smart terminal, including a memory and a processor. The memory stores a voice processing program, and when the voice processing program is executed by the processor, it implements the steps of the voice processing method in any of the above embodiments.

[0151] This application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the speech processing method in any of the above embodiments.

[0152] In the embodiments of the smart terminal and storage medium provided in this application, all the technical features of any of the above-described XX method embodiments may be included. The extended and explanatory content of the specification is basically the same as that of the embodiments of the above methods, and will not be repeated here.

[0153] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to perform the methods described in the various possible implementations above.

[0154] This application also provides a chip, including a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device with the chip installed performs the methods described in the various possible implementations above.

[0155] It is understood that the above scenarios are merely examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of this application. The technical solutions of this application can also be applied to other scenarios. For example, as those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0156] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0157] The steps in the method of this application embodiment can be adjusted, combined, or deleted according to actual needs.

[0158] The units in the device of this application embodiment can be merged, divided, and deleted according to actual needs.

[0159] In this application, the same or similar terms, concepts, technical solutions and / or application scenario descriptions are generally described in detail only when they appear for the first time. When they appear again, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of this application, the same or similar terms, concepts, technical solutions and / or application scenario descriptions that are not described in detail later can be referred to their previous relevant detailed descriptions.

[0160] In this application, the descriptions of the various embodiments have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0161] The technical features of the present application can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, controlled terminal, or network device, etc.) to execute the methods of each embodiment of this application.

[0163] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted from one storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, storage disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0164] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A speech processing method, characterized in that, Including the following steps: S1: Determine the corresponding translation processing strategy based on the obtained speaking scenario; S2: Perform the corresponding translation processing work on the speech to be processed according to the translation processing strategy.

2. The speech processing method as described in claim 1, characterized in that, The method for obtaining the speaking scenario includes at least one of the following: The speaking scenario is obtained according to the received setting instructions; The speaking scenario is obtained based on at least one of the speech features corresponding to the speech to be processed, transaction arrangement information, and environmental perception data; The speech features include at least one of the following: number of speakers, keywords, content text, and dialogue structure.

3. The speech processing method as described in claim 1 or 2, characterized in that, Step S2 includes: The speech to be processed is translated according to the content translation strategy corresponding to the speaking scenario to obtain the translation result; The translation results are processed according to the translation result processing strategy corresponding to the speaking scenario.

4. The speech processing method as described in claim 3, characterized in that, The content translation strategy includes at least one of the following: Obtain the basic terminology library corresponding to the speaking scenario; Obtain contextual knowledge information corresponding to the speaking scenario; The basic terminology database is associated with the custom terminology database to obtain terminology database association information; Based on the contextual knowledge information, the basic terminology database, and / or terminology database association information, the speech to be processed is translated to obtain a translation result.

5. The speech processing method as described in claim 4, characterized in that, The method for obtaining the custom terminology database includes at least one of the following: Identify the target user corresponding to the speaking scenario, and use the personalized terminology library associated with the target user as the custom terminology library; Identify additional topics and use the professional terminology database corresponding to the additional topics as a custom terminology database.

6. The speech processing method as described in claim 3, characterized in that, The translation result processing strategy includes at least one of the following: The translation results are displayed according to the target display strategy that matches the speaking scenario. Based on the event record template and translation results corresponding to the speaking scenario, obtain the event record file.

7. The speech processing method as described in claim 6, characterized in that, The target display strategy includes at least one of the following: Display the text information corresponding to the translation result according to the target screen display mode corresponding to the speaking scenario; Play the translated audio corresponding to the translation result.

8. The speech processing method as described in claim 6, characterized in that, It also includes at least one of the following: Obtain transaction arrangement information from the aforementioned transaction record file; Display the transaction arrangement information; The corresponding target application is determined based on the transaction attributes and preset association information corresponding to the transaction arrangement information, and the target application is controlled to record or process the transaction arrangement information.

9. A smart terminal, characterized in that, include: A memory and a processor, wherein the memory stores a speech processing program, and when the speech processing program is executed by the processor, it implements the steps of the speech processing method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the speech processing method as described in any one of claims 1 to 8.

Images