INFORMATION PROCESSING APPARATUS, PROGRAM, AND INFORMATION PROCESSING METHOD

• Main Authors: KONISHI KEISUKE, ODAMURA AKIO, FUKUE NAOFUMI
• Format: Patent
• Language: English; Japanese
• Published: 27.12.2021
• Subjects: ACOUSTICS; CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

To provide an information processing apparatus, a program, and an information processing method that can improve confidentiality in communication with a device which recognizes a voice.SOLUTION: An interaction device 100 is an information processing device which connects with a plurality of voice recognition systems recognizing voice through a network, and comprises: a generation unit which generates a plurality of pieces of utterance data from voice data; a transmission unit which transmits the plurality of pieces of utterance data to one of the plurality of voice recognition systems together with index information indicative of the order thereof; a reception unit which receives, for each of the plurality of pieces of utterance data, first recognition information indicative of a recognition result of utterance data and index information from the plurality of voice recognition systems; a merging unit which merges a plurality of pieces of first recognition information in the order based upon the index information; a response generation unit which generates first response information for responding to voice based upon the merged first recognition information; and an output unit which outputs a response to the voice based upon the first response information.SELECTED DRAWING: Figure 4 【課題】音声を認識する装置との通信に際して、機密性を向上できる情報処理装置、プログラム及び情報処理方法を提供する。【解決手段】対話装置１００は、音声を認識する複数の音声認識システムとネットワークを介して接続する情報処理装置であって、音声データから複数の発話データを生成する生成部、複数の発話データの夫々を、順序を示すインデックス情報と共に、複数の音声認識システムのいずれかに送信する送信部と、複数の音声認識システムから、複数の発話データのそれぞれについて、発話データの認識結果を示す第１認識情報とインデックス情報とを受信する受信部と、インデックス情報に基づき、複数の１認識情報を、順序で結合する結合部と、結合された第１認識情報に基づき、音声に対して応答するための第１応答情報を生成する応答生成部と、第１応答情報に基づき、音声に対する応答を出力する出力部と、を備える。【選択図】図４