SPEECH RECOGNITION SYSTEM AND INFORMATION PROCESSING DEVICE

• Main Authors: MANABE MAKOTO, SUZUKI HIDENOBU
• Format: Patent
• Language: English; Japanese
• Published: 12.12.2019
• Subjects: ACOUSTICS; CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MUSICAL INSTRUMENTS; PERFORMING OPERATIONS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION; TRANSPORTING; VEHICLES IN GENERAL; VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISEPROVIDED FOR

To provide a speech recognition system and an information processing device for responding by an easily recognizable method in accordance with the position of a user who has spoken.SOLUTION: A speech recognition system 1 comprises an information processing device 10 and a server 20 capable communicating with each other. The information processing device 10 includes a position specification unit 161 for specifying the position of an input source of a speech signal, and an output unit 13 equipped with a plurality of output devices. The server 20 includes a speech recognition unit 231 for performing speech recognition on the speech signal, a response generation unit 232 for generating a response to the content of speech recognition, and a dialog control unit 233 for selecting, on the basis of the position specified by the position specification unit, an output device from among the plurality of output devices that outputs a response.SELECTED DRAWING: Figure 1 【課題】発話したユーザの位置に応じて、認識し易い方法で応答する音声認識システムおよび情報処理装置を提供する。【解決手段】音声認識システム１は、互いに通信可能な情報処理装置１０およびサーバ２０を備え、情報処理装置１０は、音声信号の入力元の位置を特定する位置特定部１６１と、複数の出力装置を備える出力部１３と、を備え、サーバ２０は、音声信号に対して音声認識を行う音声認識部２３１と、音声認識の内容に対する応答を生成する応答生成部２３２と、位置特定部によって特定された位置に基づいて複数の出力装置から応答を出力する出力装置を選択する対話制御部２３３と、を備える。【選択図】図１