Toyota Jidosha Kabushiki Kaisha

Kyoto University

Furhat Robotics Ab

Nara Institute of Science and Technology

Narimasa Watanabe

Tatsuro Hori

Tatsuya Kawahara

Sawa Higuchi

Ryosuke Nakanishi

Martin Johansson

Katsuya Takanashi

Gabriel Skantze

Wataru Kaku

Hitoshi Yamada

Tomoya Takatani

Youhei Wakisaka

Kiyohiro Shikano

Joakim Gustafson

Randy Gomez

The control system includes a calculation unit configured to control a voice interaction system including voice recognition models, in which the calculation unit instructs, when a conversation with a target person is started, the voice interaction system to first perform voice recognition and response generation by one voice recognition model tentatively selected from among the voice recognition models, determines a voice recognition model estimated to be optimal among the voice recognition models held in the voice interaction system based on results of the voice recognition of a speech made by the target person in a voice recognition server, and instructs, when the voice recognition model estimated to be optimal is different from the one voice recognition model tentatively selected, the voice interaction system to switch the voice recognition model to the one estimated to be optimal and to perform voice recognition and response generation.

Control apparatus, voice interaction apparatus, voice recognition server, and program

A voice interaction system performs a voice interaction with a user. The voice interaction system includes: topic detection means for estimating a topic of the voice interaction and detecting a change in the topic that has been estimated; and ask-again detection means for detecting, when the change in the topic has been detected by the topic detection means, the user's voice as ask-again by the user based on prosodic information on the user's voice.

Voice interaction system, its processing method, and program therefor

A voice interaction system performs a voice interaction with a user. The voice interaction system includes: ask-again detection means for detecting ask-again by the user; response-sentence generation means for generating, when the ask-again has been detected by the ask-again detection means, a response sentence for the ask-again in response to the ask-again based on a response sentence responding to the user before the ask-again; and storage means for storing a history of the voice interaction with the user. The response-sentence generation means generates, when the response sentence includes a word whose frequency of appearance in the history of the voice interaction in the storage means is equal to or smaller than a first predetermined value, a response sentence for the ask-again formed of only this word or a response sentence for the ask-again in which this word is emphasized in the response sentence.

The control apparatus includes: a calculation unit configured to control a voice interaction apparatus including a speech section detector, the speech section detector being configured to identify whether an acquired voice includes a speech made by a target person by a set identification level and perform speech section detection, in which the calculation unit instructs, when an estimation result indicating that it is highly likely that the speech made by the target person is included in the acquired voice has been acquired from a voice recognition server, the voice interaction apparatus to change a setting in such a way as to lower the identification level of the speech section detector, and to perform communication with the voice recognition server by speech section detection in accordance with the identification level after the change.

Control method, voice interaction apparatus, voice recognition server, non-transitory storage medium, and control system

A voice interaction system capable of appropriately handling a situation to effectively prevent a response error from occurring. A speech acquisition unitacquires user speech. A feature extraction unitextracts a feature of the acquired user speech. A response determination unitdetermines a response corresponding to the extracted feature using any one of a plurality of learning models. A response execution unitperforms control in order to execute the determined response. A response error determination unitdetermines whether the executed response is an error. A learning model selection unitselects the learning model from the plurality of learning models stored in a learning model databaseaccording to a result of the determination by the response error determination unit. The response determination unitdetermines the response using the selected learning model.

Voice interaction system for interaction with a user by voice, voice interaction method, and program

A response sentence generation apparatus includes a conversion device for converting an input voice of a user into text information, an extraction device for extracting prosodic information from the input voice, a specifying device for specifying an emotion occurrence word indicating an occurrence of an emotion of the user based on the text information and the prosodic information, and a generation device for selecting a character string including the specified emotion occurrence word from the text information and generating a response sentence by performing predetermined processing on the selected character string.

Response sentence generation apparatus, method and program, and voice interaction system

A voice dialogue apparatus analyzes an acquired user's voice, generates a parrot-like response sentence and outputs the generated parrot-like response sentence. The voice dialogue apparatus includes storage means for storing the user's past voice, average calculation means for calculating an average value of voice sentence lengths each indicating a length of the user's voice based on the user's past voice, candidate generation means for combining a dependency word, which establishes a dependency relation with a noun included in the acquired user's voice, with the noun to generate a plurality of response sentence candidates, and repetition generation means for selecting, in association with the average value of the voice sentence lengths, one response sentence candidate from among the plurality of response sentence candidates and using the selected response sentence candidate as it is or processing the selected response sentence candidate to generate the parrot-like response sentence.

Voice dialogue apparatus, voice dialogue method, and non-transitory computer readable media

A syntactic analysis unitperforms a syntactic analysis for linguistic information on acquired user' speech (hereinafter simply referred to as 'user speech'). A non-linguistic information analysis unitanalyzes non-linguistic information different from the linguistic information for the acquired user speech. A topic continuation determination unitdetermines whether a topic of the current conversation should be continued or should be changed to a different topic according to the non-linguistic information analysis result. A response generation unitgenerates a response according to a result of a determination by the topic continuation determination unit

Voice interaction apparatus and voice interaction method

A voice interaction apparatus incudes voice recognition means for recognizing a voice of a user, response-sentence generation means for generating a response sentence to the voice of the user based on the recognized voice, filler generation means for generating a filler word to be inserted in a conversation, output means for outputting the generated response sentence and the generated filler word, and classification means for classifying the generated response sentence into one of predetermined speech patterns indicating predefined speech types. When the output means outputs, after the user utters a voice subsequent to the first response sentence, the filler word and outputs a second response sentence, the classification means classifies the first response sentence into one of the speech patterns, and the filler generation means generates the filler word based on the speech pattern into which the first response sentence has been classified.

Voice interaction apparatus, its processing method, and program

A syntactic analysis unitperforms a syntactic analysis for linguistic information on acquired user speech. A non-linguistic information analysis unitanalyzes non-linguistic information for the acquired user speech, the non-linguistic information being different from the linguistic information. A filler length determination unitdetermines a length of a filler according to a non-linguistic information analysis result. A filler generation unitgenerates a filler having a length corresponding to a result of a determination by the filler length determination unit. The filler length determination unitdetermines that a long filler should be generated when a syntactic analysis result needs to be used to generate a response and, otherwise, determines that a short filler should be generated. The voice output unitoutputs the response generated by the response generation unitafter outputting the filler.

A voice acquisition system includes a plurality of mobile objects each of which includes one or more microphones and is movable around a sound source; a sound source number estimating unit which estimates the number of sound sources in a vicinity of any of the mobile objects; and a control unit which controls positions of the mobile objects, wherein the control unit controls, based on the number of sound sources in a vicinity of a first mobile object, a position of a second mobile object which differs from the first mobile object, and the voice acquisition system acquires voice using both a microphone included in the first mobile object and a microphone included in the second mobile object.

Voice acquisition system and voice acquisition method

Provided is a voice interaction apparatus including an estimation unit configured to estimate whether to wait a next user's speech or to execute an output of an output speech by the voice interaction apparatus based on a user's speech input by an input unit; and the response control unit configured to, when the estimation unit could not estimate whether to wait for the user's next speech or to execute the output of the output speech by the voice interaction apparatus, respond by executing at least one of a filler output and a nodding action, the filler output being an output of a filler, i.e., a connecting utterance irrelevant to an interaction content, from the output unit, and the nodding action being an action of swinging a pseudo head part back and forth.

Voice interaction apparatus and automatic interaction method using voice interaction apparatus

A response generation method includes a step of recognizing a voice of a user, a step of analyzing a structure of the recognized voice, a step of generating a free response sentence in response to the voice of the user based on the analyzed voice structure and outputting the generated free response sentence, a step of generating the recognized voice of the user as a repeat response sentence, and a step of outputting the generated repeat response sentence before outputting the free response sentence based on the voice structure.

Response generation method, response generation apparatus, and response generation program

A processing unit is provided which executes speech recognition on speech signals captured by a microphone for capturing sounds uttered in an environment. The processing unit has: an initial reflection component extraction portion that extracts initial reflection components by removing diffuse reverberation components from a reverberation pattern of an impulse response generated in the environment; and an acoustic model learning portion that learns an acoustic model for the speech recognition by reflecting the initial reflection components to speech data for learning.

Growing community of inventors

Nagakute, Japan

Narimasa Watanabe