Abstract: A skill dispatching method for a speech dialogue platform including: receiving, by a central control dispatching service, a semantic result of recognizing a user's voice sent by a data distribution service; dispatching, by the central control dispatching service, a plurality of skill services related to the semantic result in parallel, and obtaining skill parsing results from the plurality of skill services; sorting the skill parsing results based on priorities of the skill services, and exporting a result with the highest priority to a skill realization discrimination service; when failure in realization, selecting a result with the highest priority among the rest of skill parsing results and exporting the same to the skill realization discrimination service, and when success in realization, sending the result with the highest priority to the data distribution service for feedback to the user. The method improves skill dispatching efficiency, reduces delay, and improves user experience.

Abstract: Disclosed is a speech synthesis method including: acquiring fundamental frequency information and acoustic feature information from original speech; generating an impulse train from the fundamental frequency information, and inputting it to a harmonic time-varying filter; inputting the acoustic feature information into a neural network filter estimator to obtain corresponding impulse response information; generating noise signal by a noise generator; determining, by the harmonic time-varying filter, harmonic component information through filtering processing on the impulse train and the impulse response information; determining, by a noise time-varying filter, noise component information based on the impulse response information and the noise; and generating a synthesized speech from the harmonic component information and the noise component information.

Abstract: The present disclosure discloses a method for processing man-machine dialogues, which includes: acquiring a first user voice message from a client; determining a dialogue intent corresponding to the first user voice message; determining a target duplex wake-up mode corresponding to the dialogue intent based on an intent wake-up mode table, wherein the intent-wake mode table includes duplex wake-up modes corresponding to a plurality of candidate dialogue intents respectively, and the duplex wake-up modes comprise a full-duplex wake-up mode and a half-duplex wake-up mode; and sending a wake-up mode instruction corresponding to the target duplex wake-up mode to the client, such that the client processes the first user voice message according to the target duplex wake-up mode. Using the method and apparatus for carrying out the method, the wake-up mode of the client may be switched dynamically.

Abstract: Disclosed are method and apparatus for correcting voice dialogue, including: recognizing first text information of a dialogue speech input by a user, including a first semantic keyword determined from a plurality of candidate terms; feeding back a first result with the first semantic keyword to the user based on the first text information; feeding back the plurality of candidate terms to the user in response to the user's selection of the first semantic keyword from the first result; and receiving a second semantic keyword input by the user, correcting the first text information based on the second semantic keyword, determining corrected second text information, and feeding back a second result with the second semantic keyword to the user based on the second text information. The problem of true ambiguity can be solved, while improving the fault tolerance and processing capability of the dialogue apparatus for corresponding errors.

Abstract: Disclosed is a human-computer dialogue method including determining a set number of jump topics about a target topic, and generating a topic jump map converging to the target topic based on the correlation intensions among the set number of jump topics; after an initial response to a user's dialogue request, selecting from the topic jump map a jump topic to which the user's dialogue request relates as an initial topic for a first round of recommendation; after completing a human-machine dialogue of the initial topic, determining a jump topic to jump according to the jump probability of jumping out of the initial topic to the k jump topics at the downstream level for a next round of recommendation; and gradually guiding from the initial topic to the target topic by step-by-step recommendation. A more fluent and efficient human-machine dialogue based on a clear communication goal can be realized.

Abstract: The present invention discloses a method and apparatus for awakening skills by speech, which are applied to an electronic device. The method for awakening skills by speech includes: recognizing awakening text information corresponding to a speech request message to be processed; invoking a service skill semantic model to determine a target service field corresponding to the awakening text information and a corresponding first confidence, and invoking a knowledge skill semantic model to determine a knowledge reply answer corresponding to the awakening text information and a corresponding second confidence; and selecting to awaken one of a knowledge skill and a target service skill corresponding to the target service field based on the first confidence and the second confidence. Accordingly, the probability of erroneously awakening a skill based on the speech message can be reduced.

Abstract: Disclosed are method and apparatus for correcting voice dialogue, including: recognizing first text information of a dialogue speech input by a user, including a first semantic keyword determined from a plurality of candidate terms; feeding back a first result with the first semantic keyword to the user based on the first text information; feeding back the plurality of candidate terms to the user in response to the user's selection of the first semantic keyword from the first result; and receiving a second semantic keyword input by the user, correcting the first text information based on the second semantic keyword, determining corrected second text information, and feeding back a second result with the second semantic keyword to the user based on the second text information. The problem of true ambiguity can be solved, while improving the fault tolerance and processing capability of the dialogue apparatus for corresponding errors.

Abstract: Disclosed is a speech synthesis method including: acquiring fundamental frequency information and acoustic feature information from original speech; generating an impulse train from the fundamental frequency information, and inputting it to a harmonic time-varying filter; inputting the acoustic feature information into a neural network filter estimator to obtain corresponding impulse response information; generating noise signal by a noise generator; determining, by the harmonic time-varying filter, harmonic component information through filtering processing on the impulse train and the impulse response information; determining, by a noise time-varying filter, noise component information based on the impulse response information and the noise; and generating a synthesized speech from the harmonic component information and the noise component information.

Abstract: Disclosed is a method for determining a skill field of a dialogue text including determining a skill field hit by a dialogue text input by a user, and a name semantic slot and a character semantic slot in the skill field; when the dialogue text hits a first skill field, determining whether the name semantic slot and the character semantic slot match according to a knowledge base of the first skill field; determining, if not matched, whether the name semantic slot and the character semantic slot match according to a knowledge base of a second skill field; and determining, if matched, the second skill field as the skill field of the dialogue text. Also provided is an apparatus for determining a skill field of a dialogue text. The error rate of field classification is reduced, and the skill field can be hit by the user's voice dialogue more accurately.

Abstract: Disclosed are a method and apparatus for testing a full-duplex speech interaction system. The method includes: determining a scene mixed corpus set by mixing a valid corpus set related to a test scene with an invalid corpus set unrelated to the test scene; playing each corpus audio in the scene mixed corpus set to a speech interaction device under test equipped with the full-duplex speech interaction system; acquiring a work log of the speech interaction device under test, the work log including at least a first log and a second log; and obtaining number of false responses by counting number of log entries which have false response result in the second log, and determining a false response rate based on the number of false responses and a total number of corpus audios played. End-to-end testing of the full-duplex speech interaction system is realized.

Abstract: The present invention discloses a method and apparatus for awakening skills by speech, which are applied to an electronic device. The method for awakening skills by speech includes: recognizing awakening text information corresponding to a speech request message to be processed; invoking a service skill semantic model to determine a target service field corresponding to the awakening text information and a corresponding first confidence, and invoking a knowledge skill semantic model to determine a knowledge reply answer corresponding to the awakening text information and a corresponding second confidence; and selecting to awaken one of a knowledge skill and a target service skill corresponding to the target service field based on the first confidence and the second confidence. Accordingly, the probability of erroneously awakening a skill based on the speech message can be reduced.

Abstract: A skill dispatching method for a speech dialogue platform including: receiving, by a central control dispatching service, a semantic result of recognizing a user's voice sent by a data distribution service; dispatching, by the central control dispatching service, a plurality of skill services related to the semantic result in parallel, and obtaining skill parsing results from the plurality of skill services; sorting the skill parsing results based on priorities of the skill services, and exporting a result with the highest priority to a skill realization discrimination service; when failure in realization, selecting a result with the highest priority among the rest of skill parsing results and exporting the same to the skill realization discrimination service, and when success in realization, sending the result with the highest priority to the data distribution service for feedback to the user. The method improves skill dispatching efficiency, reduces delay, and improves user experience.

Abstract: The present invention discloses an information processing method, an information control center device, and a computer-readable storage medium. The method comprises: obtaining semantic parsing information corresponding to a sound signal, the semantic parsing information including a designated time; performing a time prediction on the designated time based on a current time to determine an intended time; and generating a target instruction corresponding to the sound signal based on the intended time. With this method, the information control center device can process complex and diverse sound signals, and the designated time and target intention in a sound signal can be extracted from the semantic parsing information. Because of the time prediction on the semantic parsing information with the designated time, the designated time provided in the sound signal can be processed more accurately, and the voice interaction process is more accurate.

Abstract: An embodiment of the present invention provides a method of man-machine interaction, including: receiving first audio uploaded by a user through a client end, marking a start time and an end time of the first audio, and generating a first recognition result of the first audio using an audio decoder; determining whether the first audio is a short speech based on the start time and end time thereof, and in case of a short speech, generating a second recognition result of the second audio using the audio decoder upon receiving the second audio uploaded by the client end within a preset heartbeat protection time range, sending at least the first recognition result and the second recognition result to a language prediction model; and if it is determined that a combination of the recognition results constitutes a sentence, generating an answering instruction corresponding to the sentence, and sending the answering instruction together with a feedback time mark of the answering instruction to the client end.

Abstract: The present disclosure discloses a man-machine dialogue mode switching method, which is applicable to an electronic device. The method includes receiving a current user sentence spoken by a current user; determining whether a dialogue field to which the current user sentence belongs is a preset dialogue field; if yes, switching the current dialogue mode to a full-duplex dialogue mode; and if not, switching the current dialogue mode to a half-duplex dialogue mode. In the present disclosure, the dialogue mode is switched by determining whether the dialogue field to which the current user sentence belongs is the preset dialogue field, and the dialogue mode can be automatically switched and adjusted according to the difference of the dialogue fields, such that the man-machine dialogue is always in the most suitable dialogue mode and can be realized smoothly.

Abstract: Disclosed is a customization platform for service quality evaluation product, comprising an account management module generating a registration interface and a product creation interface for guiding a user to register and log in to customize a service quality evaluation product; an access mode configuration module generating a product access mode configuration interface for guiding user to configure an access mode for the service quality evaluation product; a voice transcription configuration module generating an industry type selection interface for guiding user to select an industry type and a corresponding voice recognition model for pre-training according to the industry type, the pre-trained voice recognition model converting an input audio file to text content; and a semantic analysis configuration module generating an evaluation information configuration interface for guiding user to input the evaluation information to perform service quality scoring according to the text content and the evaluation inf

Abstract: The present application discloses a voice dialogue processing method and apparatus. The voice dialogue processing method includes: determining a voice semantics corresponding to a user voice to be processed; determining a reply sentence for the voice semantics based on a dialogue management engine, a training sample set of which is constructed from a dialogue business customization file including at least one dialogue flow, and the dialogue flow includes a plurality of dialogue nodes in a set order; and generating a customer service voice for replying to the user voice according to the determined reply sentence.

Abstract: Disclosed is a full-duplex voice dialogue method applied to a voice dialogue terminal and including recording and uploading by an awakened voice dialogue terminal audio to a cloud server for determining a reply content and a first duration of the audio analyzed for determining the reply content; receiving by the voice dialogue terminal the reply content and the first duration sent by the cloud server; determining whether the first duration is equal to a duration from the moment awakening the voice dialogue terminal to the current moment of uploading the audio; and presenting the reply content to a user if consistent. Both the reply content determined by the cloud server and the duration of the audio is acquired, and the reply content is presented to the user only when the first duration and the second duration are determined as consistent, thereby ensuring proper reply content.

Abstract: An embodiment of the present invention provides a method of man-machine interaction, including: receiving first audio uploaded by a user through a client end, marking a start time and an end time of the first audio, and generating a first recognition result of the first audio using an audio decoder; determining whether the first audio is a short speech based on the start time and end time thereof, and in case of a short speech, generating a second recognition result of the second audio using the audio decoder upon receiving the second audio uploaded by the client end within a preset heartbeat protection time range, sending at least the first recognition result and the second recognition result to a language prediction model; and if it is determined that a combination of the recognition results constitutes a sentence, generating an answering instruction corresponding to the sentence, and sending the answering instruction together with a feedback time mark of the answering instruction to the client end.

Abstract: Disclosed is a human-computer dialogue method including determining a set number of jump topics about a target topic, and generating a topic jump map converging to the target topic based on the correlation intensions among the set number of jump topics; after an initial response to a user's dialogue request, selecting from the topic jump map a jump topic to which the user's dialogue request relates as an initial topic for a first round of recommendation; after completing a human-machine dialogue of the initial topic, determining a jump topic to jump according to the jump probability of jumping out of the initial topic to the k jump topics at the downstream level for a next round of recommendation; and gradually guiding from the initial topic to the target topic by step-by-step recommendation. A more fluent and efficient human-machine dialogue based on a clear communication goal can be realized.