Navigation voice generation method and device, computer equipment and storage medium

Abstract

The invention relates to the field of intelligent voice, and discloses a navigation voice generation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining user state information and multi-dimensional environment information in real time after voice navigation is started; setting real-time navigation voice parameters according to the user state information and the multi-dimensional environment information; and generating voice for navigation according to the real-time navigation voice parameter. According to the invention, proper real-time navigation voice parameters can be matched according to real-time user state information and multi-dimensional environment information, the character information of the navigation instruction is combined, the navigation voice with high quality, individuation and adaptability is generated, voice output can be adjusted according to user preference and real-time environment change, and the user experience is improved. The tone, speed, volume and intonation of navigation voice are adjusted in real time, different sound styles and emotional expressions are simulated, and the navigation experience of a user is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent speech, and in particular to a navigation speech generation method, device, computer equipment and storage medium. Background Art

[0002] With the development of intelligent transportation and mobile Internet technologies, voice navigation systems have become an important auxiliary tool for daily travel. Traditional voice navigation systems rely on pre-recorded voice clips to provide navigation services. These clips are usually recorded by professional voice actors or announcers and cover common navigation instructions such as "Please turn left", "Please turn right", etc. In actual use, the system selects and plays the corresponding voice clips according to the route conditions, or splices multiple clips through technical means to form a complete navigation guide. However, this method limits the diversity of the timbre of the navigation voice, because the variety of timbre depends entirely on the number of voice clips pre-recorded by the developer, which is difficult to meet the personalized needs of users. Summary of the invention

[0003] Based on this, it is necessary to provide a navigation voice generation method, device, computer equipment and storage medium to address the above technical problems in order to enhance the user's navigation experience.

[0004] A navigation speech generation method, comprising: After starting voice navigation, obtain user status information and multi-dimensional environmental information in real time; Setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; A voice for navigation is generated according to the real-time navigation voice parameters.

[0005] Optionally, the user status information includes emotional status; The real-time acquisition of user status information and multi-dimensional environment information includes: Obtaining user's voice information and / or image information; The emotional state is determined according to the voice information and / or the image information.

[0006] Optionally, the user status information includes user preference information; The real-time acquisition of user status information and multi-dimensional environment information includes: Get the user's voice information; The user preference information is extracted from the voice information.

[0007] Optionally, the multi-dimensional environmental information includes noise information and road condition information; the road condition information includes first road condition information and / or second road condition information; The real-time acquisition of user status information and multi-dimensional environment information includes: Acquiring the noise information through microphones arranged at multiple locations of the vehicle; Performing real-time recognition on the vehicle-mounted image to obtain the first road condition information; Receive the second traffic condition information provided by the navigation server.

[0008] Optionally, setting the real-time navigation voice parameters according to the user state information and the multi-dimensional environment information includes: Determining a voice timbre style according to the user status information; Determining a scene-noise level based on the multi-dimensional environmental information; The real-time navigation voice parameters are matched from the timbre-scene-noise level relationship data according to the voice timbre style and the scene-noise level.

[0009] Optionally, the user status information includes emotional status and user preference information; The determining of the voice timbre style according to the user status information comprises: determining a first timbre style of the user according to the emotional state; Determining a second timbre style of the user according to the user preference information; The voice timbre style is determined according to the first timbre style and the second timbre style.

[0010] Optionally, the multi-dimensional environmental information includes noise information and road condition information; The determining the scene-noise level according to the multi-dimensional environmental information includes: determining a noise level according to the noise information; Determining scene information according to the road condition information; The scene-noise level is determined based on the noise level and the scene information.

[0011] A navigation speech generating device, comprising: The acquisition module is used to obtain user status information and multi-dimensional environment information in real time after voice navigation is started; A parameter setting module, used for setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; A navigation voice generating module is used to generate a voice for navigation according to the real-time navigation voice parameters.

[0012] A computer device comprises a memory, a processor and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned navigation speech generation method when executing the computer-readable instructions.

[0013] One or more readable storage media storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, enable the one or more processors to execute the navigation speech generation method as described above.

[0014] The above-mentioned navigation voice generation method, device, computer equipment and storage medium can match appropriate real-time navigation voice parameters according to real-time user status information and multi-dimensional environmental information, and generate high-quality, personalized and adaptable navigation voice in combination with the text information of the navigation instructions. The voice output can be adjusted according to user preferences and real-time environmental changes, and the timbre, speaking speed, volume and intonation of the navigation voice can be adjusted in real time to simulate different voice styles and emotional expressions, thereby greatly improving the user's navigation experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0016] Figure 1 is a flowchart of a navigation speech generation method in one embodiment of the present invention; Figure 2 is a structural schematic diagram of a navigation speech generating device in one embodiment of the present invention; Figure 3 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In one embodiment, if Figure 1 As shown, a navigation speech generation method is provided, comprising the following steps S10-S30. S10: After voice navigation is started, user status information and multi-dimensional environment information are obtained in real time.

[0019] Understandably, a user, such as a driver, starts voice navigation on the vehicle by voice command / wake-up button / screen input. When performing voice navigation, it is necessary to set the parameters of the navigation voice in terms of clarity, volume, speech speed, intonation, etc., to provide the user with a clear, sufficiently loud, and accurate navigation voice so that the user can clearly hear the navigation voice and easily understand the navigation voice.

[0020] User status information refers to data related to the user's behavior, physiological state, and psychological state. User behavior includes but is not limited to: driving behavior, such as the frequency and strength of acceleration, braking, and steering; distraction, such as whether the user is operating a mobile phone, talking to a passenger, or looking at things outside the car; eye gaze direction, such as whether the user is looking at the road, the navigation screen, or elsewhere; gestures and body movements, such as whether the user reaches for something or adjusts the seat while driving. Physiological status information includes but is not limited to: heart rate, which is used to reflect the user's tension or relaxation; breathing rate, which is related to the user's tension, fatigue, or health status; blood pressure, which can reflect the user's physiological stress; body temperature, which is related to the user's comfort or health status. Psychological status information includes but is not limited to: facial emotions, such as happiness, anger, anxiety, or frustration; fatigue level, such as whether the user feels sleepy or energetic; attention level, such as whether the user is focused or distracted.

[0021] Multi-dimensional environmental information includes the in-car environment and the out-car environment. The in-car environment includes temperature, humidity, and lighting conditions. The out-car environment includes weather, traffic conditions, and road types.

[0022] User status information and multi-dimensional environmental information are collected through vehicle sensors, cameras, microphones and other monitoring devices. This information can be used to set real-time navigation voice parameters to achieve a safer and more personalized driving experience. For example, when the user is in a congested city or a construction section, the collected multi-dimensional environmental information includes background noise information. This multi-dimensional environmental information is used to adjust the real-time navigation voice parameters and automatically adjust the volume or speech speed to ensure that the user can clearly hear the navigation voice.

[0023] S20. Setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information.

[0024] Understandably, after obtaining the user status information and the multi-dimensional environmental information, the real-time navigation voice parameters can be set according to the user status information and the multi-dimensional environmental information. Here, the navigation voice parameters include but are not limited to volume, speech speed, timbre, intonation, voice clarity, voice type, voice content, and prompt time. For example, the volume can be automatically adjusted according to the noise level in the multi-dimensional environmental information; the playback speed of the voice prompt can be adjusted according to the road scene; the timbre of the voice can be adjusted according to the user's emotional state. For example, when the user status information is facial tension, and the external environment is rainy and the vehicle is in a congested state, the volume of the navigation voice is lowered, the speech speed is slowed down, the tone becomes softer, and more simplified navigation instructions are provided through the real-time navigation voice parameters to reduce user stress and distraction.

[0025] S30: Generate a voice for navigation according to the real-time navigation voice parameters.

[0026] Understandably, after obtaining the real-time navigation voice parameters, the real-time navigation voice parameters can be input into the voice generation module to generate a specific style of voice for navigation, i.e., navigation voice. The voice generation module can be constructed through flow matching models (Flow-basedGenerative Models). Flow matching models are a type of deep learning models that map data distribution to standard normal distribution through reversible transformations, thereby generating new data with a similar distribution to the original data. The voice generation module can automatically generate different voice styles and sound features by learning large-scale unsupervised data sets. The voice generation module can control voice generation through natural language prompts, which enhances the flexibility of voice generation. The voice generation module generates natural and fluent navigation voice based on the real-time navigation voice parameters and the text information of the navigation instructions. Here, the voice generation module based on the flow matching model has a strong The navigation voice generation method provided in this embodiment can match appropriate real-time navigation voice parameters according to real-time user status information and multi-dimensional environmental information, and generate high-quality, personalized and adaptable navigation voice in combination with the text information of the navigation instructions. It can adjust the voice output according to user preferences and real-time environmental changes, and adjust the timbre, speaking speed, volume and intonation of the navigation voice in real time, simulate different voice styles and emotional expressions, and greatly enhance the user's navigation experience.

[0027] Optionally, the user status information includes an emotional state; step S10, namely, obtaining the user status information and multi-dimensional environmental information in real time, includes: S101, obtaining voice information and / or image information of a user; S102: Determine the emotional state according to the voice information and / or the image information.

[0028] Understandably, the user's voice information can be collected through a microphone set inside the vehicle. The user's image information is captured using a camera inside the vehicle. The voice information is recognized by a trained voice emotion recognition model to obtain the user's emotional state, such as happiness, sadness, anger, surprise, etc. Here, the voice emotion recognition model can be based on RNN (recurrent neural network), LSTM (long short-term memory network), GRU (gated recurrent unit) or Transformer. The image information is recognized by a trained image emotion recognition model to obtain the user's emotional state. Here, the image emotion recognition model can be based on CNN (convolutional neural network), especially pre-trained models such as VGG and ResNet.

[0029] The user's emotional state can be obtained by using a single voice information or image information. Alternatively, the voice information and image information can be recognized at the same time to obtain their respective recognition results, and then the user's emotional state can be obtained by combining the two recognition results.

[0030] This embodiment can obtain the user's accurate emotional state by analyzing the user's voice information and image information, accurately guide the setting of navigation voice parameters, and improve the user experience.

[0031] Optionally, the user status information includes user preference information; step S10, namely, obtaining the user status information and multi-dimensional environment information in real time, includes: S103, obtaining the user's voice information; S104: Extracting the user preference information from the voice information.

[0032] Understandably, the user status information includes user preference information. The user preference information can be directly extracted from the user's voice information. For example, if the user issues a voice command: use a lively male voice for navigation, the user preference information that can be extracted is: lively, male voice.

[0033] The method provided in this embodiment can directly extract user preference information through voice information, which greatly reduces the difficulty of extracting user preference information.

[0034] Optionally, the multi-dimensional environmental information includes noise information and road condition information; the road condition information includes first road condition information and / or second road condition information; Step S10, namely, obtaining user status information and multi-dimensional environment information in real time, includes: S105, acquiring the noise information through microphones arranged at multiple locations of the vehicle; S106, performing real-time recognition on the vehicle-mounted image to obtain the first road condition information; S107: Receive the second road condition information provided by the navigation server.

[0035] Understandably, multi-dimensional environmental information includes noise information and road condition information. Microphones can be set at multiple locations in the vehicle to use the noise at different locations in the vehicle. In some examples, microphones can be set at the driver's headrest, the middle of the roof, the center console, the steering wheel, the rear seat, the door, etc. The noise information includes the noise at each location.

[0036] The road condition information includes the first road condition information and / or the second road condition information. The first road condition information is the result of real-time recognition of the vehicle-mounted image. The current vehicle-mounted image can be recognized by a trained road condition recognition model to obtain the first road condition information. The first road condition information may include congestion / unobstructed traffic, whether it is a construction site, city / highway, etc. The second road condition information provided by the navigation server may also be received. The content of the second road condition information is similar to that of the first road condition information, but the acquisition method is different.

[0037] This embodiment can be used to adjust real-time navigation voice parameters by collecting noise information to enhance the voice of the navigation voice; by collecting road condition information, it can be used to adjust real-time navigation voice parameters to adjust the timbre and content of the navigation voice to enhance the user's driving experience.

[0038] Optionally, step S20, i.e., setting the real-time navigation voice parameters according to the user state information and the multi-dimensional environment information, includes: S201, determining a voice timbre style according to the user status information; S202, determining a scene-noise level according to the multi-dimensional environmental information; S203: Match the real-time navigation voice parameters from the timbre-scene-noise level relationship data according to the voice timbre style and the scene-noise level.

[0039] Understandably, a suitable voice timbre style can be selected according to the user status information. For example, when a user is driving at 8 pm, it is detected that the user looks tired, and the voice recognition analysis finds that the driver's tone is slightly impatient. At this time, the user status information obtained includes: tired, slightly impatient; the matching voice timbre style can be: gentle + soothing. In this way, the formal timbre style originally used (faster speaking speed, lower pitch) is adjusted to a softer, slower speaking speed timbre style, which can help reduce the driver's tension and fatigue.

[0040] The scene-noise level can be determined based on multi-dimensional environmental information. Multi-dimensional environmental information includes noise information and road condition information. The corresponding scene can be matched according to the road condition information. The scene can be defined according to actual needs, such as normal driving, traffic congestion, accident scene, construction area, driving in bad weather, etc. The noise level can be defined according to actual needs. For example, the noise level can be defined according to the noise volume, and the noise level can be divided into quiet, medium, noisy, very noisy, etc. For another example, the noise level can be defined according to the type of noise source, and the noise level can be divided into vehicle horn sound (medium), crowd noise (medium), and construction site noise (loud).

[0041] The timbre-scene-noise level relationship data can be a computational model constructed using historical data and test data. By inputting the voice timbre style and scene-noise level into the calculation module, the corresponding real-time navigation voice parameters can be calculated. First, the initial timbre-scene-noise level relationship data is constructed through test data, and user preference settings and historical behavior data are recorded. Continuously learn from these interaction data, adjust the timbre-scene-noise level relationship data, and improve long-term user experience. In some examples, the timbre-scene-noise level relationship data can be represented as a two-dimensional table (indexed by timbre and scene-noise level) or a three-dimensional table (indexed by timbre, scene, and noise level).

[0042] This embodiment can meet the personalized needs of different users and make users feel more comfortable and satisfied by determining the voice timbre style according to user status information; by determining the scene-noise level according to multi-dimensional environmental information, it can ensure that the navigation voice remains clear and audible in different noise environments; by matching real-time navigation voice parameters from timbre-scene-noise level relationship data, the voice system can be quickly adjusted to adapt to the ever-changing environment and user status.

[0043] Optionally, the user status information includes emotional state and user preference information; step S201, i.e., determining the voice timbre style according to the user status information, includes: S2011, determining a first timbre style of the user according to the emotional state; S2012, determining a second timbre style of the user according to the user preference information; S2013. Determine the speech timbre style according to the first timbre style and the second timbre style.

[0044] Understandably, the timbre relationship between emotion and timbre can be pre-constructed, and after determining the emotional state, the corresponding first timbre style can be matched. For example: happy → brisk, lively; sad → gentle, slow. The user's second timbre style can be determined based on the user preference information. Here, if the user updates the user preference information through voice commands, the latest user preference information is used, otherwise the last recorded user preference information is used. Then, the final voice timbre style is determined by combining the two dimensions of emotional state and user preference.

[0045] This embodiment determines the first timbre style according to the user's emotional state, which can better match the user's emotions and provide emotional support and comfort; determines the second timbre style according to the user's preference information to ensure that the navigation voice meets the user's personal preferences, thereby improving user satisfaction; and determines the final voice timbre style by combining the two dimensions of emotional state and user preference, which can balance different needs and factors and provide a more comprehensive and satisfactory solution. Since the voice style can be dynamically adjusted according to the user's current emotions and user preference information, the navigation experience is more flexible and varied.

[0046] Optionally, the multi-dimensional environmental information includes noise information and road condition information; step S202, i.e., determining the scene-noise level according to the multi-dimensional environmental information, includes: S2021. Determine a noise level according to the noise information; S2022, determining scene information according to the road condition information; S2023. Determine the scene-noise level according to the noise level and the scene information.

[0047] Understandably, the noise level can be determined based on the noise information. If the noise information includes noise at multiple locations, the noise level can be determined using the weighted sum of these noises. In some examples, the sound pressure level of the noise can be calculated and compared with the noise level classification standard to determine the corresponding noise level. It should be noted that for noise at different locations, it can also be used to set the volume output of speakers at different locations in the car to further enhance the noise suppression effect.

[0048] The corresponding scene can be matched according to the road condition information. The scene can be defined according to actual needs, such as normal driving, traffic congestion, accident scene, construction area, driving in bad weather, etc. Combining the noise level and scene information, the scene-noise level can be generated.

[0049] This embodiment can adjust the volume, speaking speed and pitch of the navigation voice by determining the noise level to ensure that information can be clearly conveyed even in a noisy environment; determining scene information based on road condition information can enable the navigation system to more accurately understand the user's driving environment and thus provide more appropriate navigation instructions and services; combining noise level and scene information can provide users with a more personalized navigation experience.

[0050] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0051] In one embodiment, a navigation speech generating device is provided, and the navigation speech generating device corresponds to the navigation speech generating method in the above embodiment. Figure 2 As shown, the navigation speech generating device includes an acquisition module 10, a parameter setting module 20 and a navigation speech generating module 30. The detailed description of each functional module is as follows: The acquisition module 10 is used to acquire user status information and multi-dimensional environment information in real time after voice navigation is started; A parameter setting module 20, used to set real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; The navigation voice generating module 30 is used to generate voice for navigation according to the real-time navigation voice parameters.

[0052] Optionally, the user status information includes an emotional state; the acquisition module 10 includes: An acquisition unit, used to acquire voice information and / or image information of a user; The emotional state determining unit is used to determine the emotional state according to the voice information and / or the image information.

[0053] Optionally, the user status information includes user preference information; the acquisition module 10 includes: A voice information acquisition unit is used to acquire the user's voice information; The user preference information extraction unit is used to extract the user preference information from the voice information.

[0054] Optionally, the multi-dimensional environmental information includes noise information and road condition information; the road condition information includes first road condition information and / or second road condition information; the acquisition module 10 includes: A noise information acquisition unit, used to acquire the noise information through microphones arranged at multiple positions of the vehicle; Acquiring a first road condition information unit, used to perform real-time recognition of the vehicle-mounted image to obtain the first road condition information; The second traffic condition information acquisition unit is used to receive the second traffic condition information provided by the navigation server.

[0055] Optionally, the parameter setting module 20 includes: A timbre style determination unit, used to determine the voice timbre style according to the user status information; A scene-noise level determination unit, configured to determine a scene-noise level according to the multi-dimensional environmental information; The real-time navigation voice parameter matching unit is used to match the real-time navigation voice parameters from the timbre-scene-noise level relationship data according to the voice timbre style and the scene-noise level.

[0056] Optionally, the user status information includes emotional status and user preference information; and the timbre style determination unit includes: Determine a first timbre style unit, used to determine a first timbre style of the user according to the emotional state; A second timbre style determination unit is used to determine a second timbre style of the user according to the user preference information; The speech timbre style determining unit is used to determine the speech timbre style according to the first timbre style and the second timbre style.

[0057] Optionally, the multi-dimensional environmental information includes noise information and road condition information; and the scene-noise level determination unit includes: a noise level determining unit, configured to determine a noise level according to the noise information; A scene information determination unit, used to determine scene information according to the road condition information; A scene-noise level generating unit is used to determine the scene-noise level according to the noise level and the scene information.

[0058] For the specific definition of the navigation voice generating device, please refer to the definition of the navigation voice generating method above, which will not be repeated here. Each module in the above navigation voice generating device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0059] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer-readable instructions. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer-readable instructions are executed by the processor, a navigation voice generation method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0060] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer-readable instructions to implement the following steps: After starting voice navigation, obtain user status information and multi-dimensional environmental information in real time; Setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; A voice for navigation is generated according to the real-time navigation voice parameters.

[0061] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage media store computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the following steps are implemented: After starting voice navigation, obtain user status information and multi-dimensional environmental information in real time; Setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; A voice for navigation is generated according to the real-time navigation voice parameters.

[0062] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0063] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0064] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A navigation speech generation method, characterized in that: include: After starting voice navigation, obtain user status information and multi-dimensional environmental information in real time; Setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; A voice for navigation is generated according to the real-time navigation voice parameters.

2. The navigation speech generation method according to claim 1, characterized in that: The user status information includes emotional status; The real-time acquisition of user status information and multi-dimensional environment information includes: Obtaining user's voice information and / or image information; The emotional state is determined according to the voice information and / or the image information.

3. The navigation speech generation method according to claim 1, characterized in that: The user status information includes user preference information; The real-time acquisition of user status information and multi-dimensional environment information includes: Get the user's voice information; The user preference information is extracted from the voice information.

4. The navigation speech generation method according to claim 1, characterized in that: The multi-dimensional environmental information includes noise information and road condition information; the road condition information includes first road condition information and / or second road condition information; The real-time acquisition of user status information and multi-dimensional environment information includes: Acquiring the noise information through microphones arranged at multiple locations of the vehicle; Performing real-time recognition on the vehicle-mounted image to obtain the first road condition information; Receive the second traffic condition information provided by the navigation server.

5. The navigation speech generation method according to claim 1, characterized in that: The setting of real-time navigation voice parameters according to the user status information and the multi-dimensional environment information includes: Determining a voice timbre style according to the user status information; Determining a scene-noise level based on the multi-dimensional environmental information; The real-time navigation voice parameters are matched from the timbre-scene-noise level relationship data according to the voice timbre style and the scene-noise level.

6. The navigation speech generation method according to claim 5, characterized in that: The user status information includes emotional status and user preference information; The determining of the voice timbre style according to the user status information comprises: determining a first timbre style of the user according to the emotional state; Determining a second timbre style of the user according to the user preference information; The voice timbre style is determined according to the first timbre style and the second timbre style.

7. The navigation speech generation method according to claim 5, characterized in that: The multi-dimensional environmental information includes noise information and road condition information; The determining the scene-noise level according to the multi-dimensional environmental information includes: determining a noise level according to the noise information; Determining scene information according to the road condition information; The scene-noise level is determined based on the noise level and the scene information.

8. A navigation speech generating device, characterized in that: include: The acquisition module is used to obtain user status information and multi-dimensional environment information in real time after voice navigation is started; A parameter setting module, used for setting real-time navigation voice parameters according to the user status information and the multi-dimensional environment information; A navigation voice generating module is used to generate a voice for navigation according to the real-time navigation voice parameters.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the navigation speech generation method according to any one of claims 1 to 7 is implemented.

10. One or more readable storage media storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute the navigation speech generation method according to any one of claims 1 to 7.

Images