40results about How to "Improve voice interaction experience" patented technology

The present application provides a speech synthesis method and related equipment. The method includes the following steps that: the identity of a user is determined according to the current input speech of the user; an acoustic model is obtained from an acoustic model library according to the current input speech; basic speech synthesis information is determined according to the identity of the user, wherein the basic speech synthesis information characterizes variable quantities in the preset sound speed, preset volume, and preset pitch of the acoustic model; a reply text is determined; enhanced speech synthesis information is determined according to the reply text and context information, wherein the enhanced speech synthesis information characterizes variable quantities in the preset timbre, tone and preset rhythm of the acoustic model; and speech synthesis is performed on the reply text through the acoustic model according to the basic speech synthesis information and the enhancedspeech synthesis information, so that reply speech for the user can be obtained. With the speech synthesis method and related apparatus provided by the embodiments of the invention adopted, a device can provide a personalized speech synthesis effect to the user during a man-machine interaction process, and therefore, the speech interaction experience of the user can be improved.

The invention discloses a voice interaction control method and device for intelligent equipment, and the method comprises the steps: monitoring and collecting a voice signal, sent by an intelligent equipment user, in real time; carrying out the voice recognition of the collected voice signal; wakening the corresponding functions of the intelligent equipment according to the voice recognition result of the voice signal, and determining whether to control the intelligent equipment to move or not: obtaining the position of the user if the intelligent equipment is controlled to move, controlling the intelligent equipment to move towards the user, shortening the distance between the intelligent equipment and the user, and recognizing another voice signal sent by the user; or else, controlling the intelligent equipment to carry out the corresponding operation according to the voice recognition result. According to the technical scheme of embodiment of the invention, the method controls the intelligent equipment to move towards the user according to the voice recognition result when a voice instruction of the user cannot be heard clearly because of long distance, thereby achieving the near-field voice interaction, ironing out the defect that a far-field voice recognition effect is poor, and providing natural and smooth interaction experience for the user.

The invention discloses a natural human-computer voice interaction method. The method comprises: (1) signal acquisition is carried out; to be specific, a microphone array is used for collecting sound signals of a sound source, the orientation of the sound source is determined based on the sound signals collected by microphones at different places in the microphone array, and a camera is used for collecting an image signal of the orientation of the sound source; (2), sound source identity identification is carried out; to be specific, according to the collected image signal, the identity of the sound source is identified; (3), speaking object identification is carried out; to be specific, according to the collected image signal and sound signals, a speaking object is identified based on a hot word monitoring and slight line analysis algorithm; and (4), on the basis of the collected sound signals, whether a response to the sound source needs to be made is determined. Correspondingly, the invention also discloses a natural human-computer voice interaction system. The natural human-computer voice interaction method and system can be applied to human-computer voice interaction to enhance the human-computer voice interaction experience, so that the user can obtain a natural feeling during the human-computer voice interaction process.

The embodiment of the invention provides a voice interaction method, device and an intelligent terminal. The method comprises the following steps: detecting noise information of a current interactionenvironment when receiving a voice interaction instruction, wherein the noise information comprises noise volume and noise frequency; determining main frequency used for synthesizing response voice corresponding to the voice interaction instruction according to the noise frequency; synthesizing response voice according to the main frequency; determining volume at which the response voice is playedaccording to the noise volume, the noise frequency and the main frequency of the response voice; playing the response voice at the determined volume. Through the above technical scheme, the main frequency of the response voice and the playing volume can be dynamically adjusted according to noise information on the current interaction environment such that a user can acquire better voice interaction experience under any interaction environment.

The present invention provides a voice recognition method, a client and a terminal device. The method comprises: acquiring an original voice recognition result of a voice input by a user, and parsing a voice recognition scenario of the user according to the original voice recognition result; according to the voice recognition scenario, acquiring keyword information that needs to be corrected and a polyphone in each piece of keyword information from the original voice recognition result; generating one or more junk words containing the polyphone according to the keyword information that needs to be corrected and the polyphone in each piece of keyword information; according to the voice recognition scenario, acquiring actual information, which corresponds to the voice recognition scenario, in a terminal device, and matching the junk word with the actual information, screening out a correct polyphone, and filling the keyword information that needs to be corrected with the correct polyphone, so as to obtain a correct keyword; and according to the correct keyword, generating a final voice recognition result that coincides with a current voice recognition scenario.

The invention relates to a voice signal response method, electronic equipment, a medium and a system. The method comprises the steps that multiple electronic devices receive voice signals; for each electronic device, a target sound source point correlated with the voice signal is determined; for each electronic device, direct arrival sound energy correlated with the voice signal is determined according to the target sound source point; and at least one electronic device with the direct arrival sound energy meeting a predetermined condition is selected from the multiple electronic devices, andthe selected electronic devices respond to the voice signals. A pickup decision system based on the multiple electronic devices is realized, the system can respond to a voice of a user more accurately, more reasonably and more pertinently, and therefore voice interaction experience is improved.

The invention discloses a voice interaction method based on voiceprint recognition, which comprises the following steps of: receiving a voice command of a user; according to the voice command of the user, carrying out voiceprint recognition process, according to the voiceprint recognition result, starting voice interactive processing, wherein when the user to which the voice command belongs is recognized, responding processing is carried out according to the user identity determined by the voiceprint recognition; otherwise, voice wake-up processing is carried on the voice command, and responseprocessing is carried out according to the voice wake-up processing result. The invention also provides a voice interaction device based on the voiceprint recognition. According to the method and device provided by the invention, the flow of a voice conversation can be reduced, a wake-up phase of wake-up words is removed, and the voiceprint is simultaneously used as a medium for wake-up / recognition and a data source, so that the voice interaction experience of a user is improved. A voiceprint ID is used for distinguish users, skill customization meeting different customers is carried out, a voice recognition device is connected with the voiceprint ID, so that the universality of the voice recognition device is improved.

The invention discloses a service robot interaction system, which comprises a controller, a voice acquisition module, a voice recognition module, a robot sound production module controller, a display screen, a microphone and a card reader, and is characterized in that the display screen, the microphone, the card reader and the voice acquisition module are respectively arranged at the outer surface of a shell; the controller, the voice recognition module and the robot sound production module controller are respectively arranged inside the shell; the card reader is used for reading identity card information of a client and transmitting the acquired identity card information to the controller to analyze and store; the controller adjusts the sound production speed and the volume of a robot through controlling the robot sound production module controller according to the identity card information of the client; and the voice acquisition module and the voice recognition module are mutually cooperate to recognize a voice instruction of the user. The service robot voice interaction system overcomes a problem of poor user experience caused by simple function and fixed volume and speed of the interaction voice of a voice interaction system in the prior art.

The invention discloses a voice interaction method and device. The method comprises the following steps: acquiring voice information acquired by intelligent equipment; determining a response type of the voice information according to a first task currently executed by the intelligent equipment; determining response feedback corresponding to the voice information according to the response type; andcontrolling the intelligent equipment to output response feedback. Compared with the prior art, in this method, after any voice information is acquired by intelligent equipment; the intelligent equipment is executing the first task at present, the response type of the voice information and the corresponding response feedback can also be determined; and the response feedback is output, therefore,when the intelligent equipment is executing the task at present, targeted response feedback can be output to any acquired voice information, global response interaction is realized, feedback exists everywhere, and a user is ensured to receive the response feedback in voice interaction with the robot at any time and in any scene, so that good voice interaction experience is formed between the userand the intelligent equipment.

The invention discloses a voice interaction method, a voice interaction device, computing equipment and a storage medium, which are used for solving the technical problem that the response of the equipment is relatively mechanical and lacks the sense of reality of human-computer interaction during human-computer interaction. The method comprises the following steps: generating a response text based on acquired user interaction voice; obtaining a target voice resource associated with the response text according to a preset obtaining strategy; performing audio feature extraction on the target voice resource to obtain note feature information corresponding to the target voice resource; synthesizing the response text by using the note characteristic information to obtain equipment response voice corresponding to the response text; and outputting the equipment response voice.

The invention provides a device response processing method and device, wherein the method comprises the steps: receiving an audio signal which is collected by a microphone module and comprises a wake-up word; determining audio signal energy corresponding to a wake-up word in the audio signal, and determining a variance of a positioning result of the audio signal; sending the audio signal energy corresponding to the wake-up word, the variance of the positioning result of the audio signal and the device identifier to a predetermined main control device; and responding to the audio signal according to the response prompt message fed back by the main control device, wherein the problem that a response device that the user wants to wake up cannot be accurately determined when multiple devices are wakened up by the same wake-up word in the prior art can be solved, the voice of the user can be accurately and reasonably responded, and the voice interaction experience is improved.

The objective of the invention lies in providing a method, device and system for executing a task corresponding to a natural language command. Specifically, the method comprises the steps: obtaining the natural language command inputted by a user currently; carrying out the analysis of the natural language command, so as to obtain the task corresponding to the natural language command; dividing the task into at least two subtasks which have the execution sequential relation; and transmitting each of the subtasks to the device for executing the corresponding subtask, so as to enable the task to be executed. Compared with the prior art, the method achieves a purpose that the user can operate a plurality of intelligent devices to cooperate to meet the demands, expressed by the natural language demand, of the user through the natural language demand, and there is no need of interaction with each intelligent device, so the operation is convenient. The method reduces the interaction time of the user, improves the interaction efficiency, and also improves the interaction experience of the intelligent devices of the user.

The invention aims to provide a method, a device and a system for natural language content title disambiguation. Specifically, actual meaning information corresponding to a content title obtained after a natural language command of a user is converted is determined from multiple pieces of meaning information according to device type information of an output device, and content corresponding to the content title is output according to the actual meaning information. Therefore, when the meaning expressed by the user in a natural language is converted into a meaning which is expressed clearly but the content indicated by the meaning is uncertain, the true meaning of the user can be understood, the graph recognition accuracy of the user is improved, and the speech interactive experience of the user is also improved.

The application discloses a dialogue process intention extraction and statement prompting method and system and electronic equipment thereof. The dialogue statement corpora are exported in a formattedmode through a task-type robot management background, a dialogue statement corpus is generated, a task-type robot service scene lexicon is collected, corpus processing is conducted on statements input by a user in the dialogue process; keywords of a statement input by a user are obtained, then a user intention is extracted through the keywords, and finally a corresponding statement is displayed to the user in real time based on an intention extraction result to provide a reference for the user so as to improve user experience. According to the method, the characteristics of voice interactionof the task-based robot are fully combined, the speaking intention of the user can be rapidly extracted from the current input statement of the user, the accurate statement set in the robot corpus triggering the intention can be provided for the user for reference in real time, and the voice interaction experience of the task-based robot can be greatly improved.

The invention provides a voice interaction method and device applied to a voice interaction system, and the method comprises the following steps: receiving a target voice entry from a user when the voice interaction system is in a voice activation state; judging whether the target voice entry is an online voice entry or not; if the target voice entries are online voice entries, recognizing whetherthe target voice entries include offline voice entries located in a preset blacklist or not, wherein the blacklist includes at least one offline voice entry, and the offline voice entries are voice entries used for conducting offline voice control over the voice interaction system; and if the target voice entries include offline voice entries in the blacklist, ending the voice interaction for thetarget voice entries. According to the scheme, the voice interaction experience of the user can be improved.

The invention provides a human-computer interaction method, a terminal and a computer readable storage medium. The method comprises the following steps: acquiring current voice data, and then identifying a first emotion of the voice data; wherein the first emotion is obtained by one or more of a text emotion recognition result or a voice emotion recognition result, determining a second emotion corresponding to the first emotion state, and outputting response voice for the voice data, wherein the response voice has the second emotion. According to the technical scheme, the problem that the emotion matching degree of the response voice and the user is low in an existing voice interaction scene can be solved, and the sense of reality and interestingness of the voice interaction process are enhanced.

The invention discloses a voice recognition conversion method, which comprises the following steps: obtaining voice data, and performing voice recognition on the voice data to generate text information to be output; performing conversion analysis on the to-be-output text information to obtain a to-be-converted text; and performing conversion condition judgment on the to-be-converted text, processing the to-be-output text information according to a judgment result, and generating and outputting an identification result. The invention further discloses a voice recognition conversion system, according to the method and the system disclosed by the invention, the recognition result can be more humanized, and the voice interaction experience feeling of the user is improved.

The invention provides a voice electric appliance control method and device, a storage medium and a voice electric appliance. The method comprises the steps of collecting an environment image of an environment where the voice electric appliance is located through a binocular camera; determining a relative position relationship between a target user and a loudspeaker of the voice electric appliancebased on the environment image; and controlling a loudspeaker of the voice electric appliance according to the relative position relationship between the target user and the loudspeaker. According tothe scheme provided by the invention, the sound output of the loudspeaker can be dynamically adjusted.

The invention discloses a method and a system for adjusting volume, after the audio signal is collected from the environment, dividing the audio signal into a plurality of short-time audio frames, when the short-term energy in the short-term audio frame is greater than the short-term energy threshold, when the short-time frequency is greater than the short-time frequency threshold, determining that the corresponding short-time audio frame is in a speech mixing state, by processing all the short-time audio frames in the speech mixing state, the short-time audio frames higher than the referenceaudio frames are lowered to the reference audio frames, and the short-time audio frames lower than the reference audio frames are raised to the reference audio frames, thereby realizing automatic volume adjustment. The invention solves the problem that the volume fluctuates greatly when the voice interacts, and saves the process that the user manually adjusts the volume of the player, thereby improving the voice interaction experience and enabling the user to carry out normal voice communication.

The invention discloses a voice recognition correction method. The method comprises the following steps: in a voice recognition process, when it is monitored that a user deletes a voice recognition result, obtaining voice information re-input by the user; performing big data comparison on the voice information to obtain a voice recognition result sequence corresponding to the voice information; and displaying the voice recognition result sequence according to a preset rule. The invention further discloses a voice recognition correction device and a computer readable storage medium. According to the invention, the voice recognition result of the user can be corrected when an error occurs in the voice recognition process of the user.

The invention discloses a voice synthesis method and device, electronic equipment and a storage medium, and relates to the technical field of voice processing. The method comprises the following steps: in a voice broadcasting process, when an input voice of a user is detected, recognizing voice features of the input voice; according to the voice features, determining voice parameters used for broadcasting voice, wherein the voice parameters are used for generating voice corresponding to the voice parameters for to-be-broadcasted text information; based on grammar analysis on the to-be-broadcasted text information, adding identification information to the to-be-broadcasted text information to obtain target text information; and generating a target voice for broadcasting based on the voice parameters and the target text information. Therefore, the corresponding voice parameters can be determined according to the voice features of the user, and the personalized target voice for the user is generated based on the voice parameters, so that the voice interaction experience of the user is improved.

The invention discloses a speech control method of a smart television and the smart television. The problem of inaccurate speech recognition of the smart television is solved. The method comprises thesteps that a number of steerable controls are acquired based on the current display interface of the smart television; each steerable control is sorted and marked according to the position coordinates of the steerable controls on the display interface, and a mark and a corresponding control instruction are mapped and saved in a recognition library; control speech sent by a user is acquired, wherein the control speech comprises marked speech information; the control speech is compared with the recognition library, and a control instruction corresponding to the control speech is determined according to the comparison result; and the operation corresponding to the control instruction is executed. The smart television comprises the speech control method of the smart television provided by thetechnical scheme.

The invention aims to provide a method, device and system for natural language content title disambiguation. Specifically, the method comprises the steps of outputting device type information of a device; determining a natural language command of the user from the semantic item information, and converting the natural language command to obtain actual semantic item information corresponding to thecontent title, and outputting the content corresponding to the content title according to the actual meaning item information, so that the real meaning of the user can be understood when the meaning expressed by the natural language of the user is converted into the meaning which is explicit in expression and the referred content is uncertain, the accuracy of user graph recognition is improved, and the voice interaction experience of the user is also improved.

The invention provides voice equipment, a voice interaction method and device thereof and a storage medium, and the method comprises the steps: reading a no-matching answer question list when the voice equipment meets a first predetermined condition; inquiring whether questions without matched answers stored in the question list without matched answers have matched answers or not at present; and if the matched answer of any question without the matched answer is queried, sending corresponding first reminding information. According to the scheme provided by the invention, the question which isput forward by the user but has no answer can be inquired again, the user is reminded, and the voice interaction experience of the user is improved.

The invention provides a directional sound receiving device and a vehicle-mounted voice triggering method. The device is applied to a vehicle and comprises a plurality of voice wake-up buttons and a plurality of microphone arrays, the wake-up voice buttons are distributed at one or more positions of a main driving position, a co-driving position and a rear row position of the vehicle, the wake-upvoice buttons are electrically connected with one or more microphone arrays, and the microphone arrays are used for collecting voice signals of passengers. Embodiments according to the present invention, voice signals can be directionally collected for passengers who open the wake-up voice button, the voice assistant awakening accuracy of passengers is improved, meanwhile, the microphone array atthe corresponding position directionally collects the voice signals, the accuracy of collecting the voice signals of the passengers is improved, the voice interaction experience of the passengers at different positions in the vehicle is improved, and the passengers awaken the voice assistant through the buttons, so that the use cost of voice service can be reduced.

The purpose of the present invention is to provide a method, device and system for natural language content title disambiguation. Specifically, by determining the user's natural language command from multiple meaning information according to the device type information of the output device, the actual meaning information corresponding to the content title is obtained after conversion, and outputting the content title based on the actual meaning information. corresponding content, so as to realize that when the meaning expressed by the user's natural language is converted into a clear expression, but the content it refers to is uncertain, the user's true meaning can be understood, which improves the accuracy of user map recognition and also improves the user experience. Voice interaction experience.