Voice processing apparatus and computer program for voice processing

音声処理装置及び音声処理用コンピュータプログラム

Abstract

【課題】利用者が手を使わずに入力作業を行えるという音声処理の利点を損なわない音声処理トリガを提供する。 【解決手段】音響の入力を許容する音響入力部201から出力されたアナログ信号をデジタル信号に変換して音声処理を実行する(音声認識部205)に際しての音声処理トリガとして、デジタル信号に変換された音響が音声としての特徴量を取得しにくい音響であるかどうかの尤度を計算し、当該計算結果に基づいて当該音響が音声としての特徴量を取得しにくい音響であるかどうかの判定処理を実行し(認識指示部203)、デジタル信号に変換された音響が音声としての特徴量を取得しにくい音響であるとの判定結果の出力を音声処理トリガとして扱うようにした。 【選択図】図2
PROBLEM TO BE SOLVED: To provide a voice processing trigger which does not impair advantage of voice processing that a user performs input operation without using hands. SOLUTION: As the voice processing trigger when voice processing is performed by converting an analog signal which is output from a sound input section 201 for accepting sound input, to a digital signal (a voice recognition section 205), likelihood is calculated concerning whether the sound which is converted to the digital signal is the sound whose feature amount as voice is hard to acquire, or not, and determination processing is performed about whether the sound is the sound whose feature amount as the voice is hard to acquire, or not, based on the calculation result (a recognition indication section 203), and output of the determination result that the sound which is converted to the digital signal is the sound whose feature amount as voice is hard to acquire, is processed as the voice processing trigger. COPYRIGHT: (C)2007,JPO&INPIT

Claims

Description

Topics

Download Full PDF Version (Non-Commercial Use)

Patent Citations (0)

    Publication numberPublication dateAssigneeTitle

NO-Patent Citations (0)

    Title

Cited By (0)

    Publication numberPublication dateAssigneeTitle