会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • SPEECH RECOGNITION SYSTEM
    • 语音识别系统
    • EP1691344B1
    • 2009-06-24
    • EP04818533.4
    • 2004-11-12
    • HONDA MOTOR CO., LTD.
    • NAKADAI, KazuhiroTSUJINO, HiroshiOKUNO, Hiroshi 1102, Form Higashi Toin SanjyoYAMAMOTO, Shunichi
    • G10L15/06H04R3/00
    • G10L15/20G10L21/028G10L2021/02166
    • There is provided a speech recognition device capable of recognizing a speech with a high accuracy even when a speaker or mobile body having the speech recognition device is moving. The speech recognition device recognizes a speech of a particular speaker HMj from an acoustic signal detected by a plurality of microphones M and converts it into character information. The speech recognition device includes: a sound source localization unit (10) for localizing the sound source direction thetaHMj of the speaker HMj; a sound source isolation unit (20) for isolating the speech signal of the speaker HMj from the acoustic signal according to the sound source direction thetaHMj; an acoustic model storage unit (49) containing a direction-dependent acoustic model H(thetan) corresponding to intermittent plurality of directions; an acoustic model synthesis unit (40) for obtaining an acoustic model of the sound source direction thetaHMj according to the direction-dependent acoustic model H(thetan) of the acoustic model storage unit (49) and making the acoustic model storage unit (49) store the result; and a speech recognition unit (50) for using the acoustic model synthesized by the acoustic model synthesis unit (40) so as to perform speech recognition of the audio signal isolated by the sound source isolation unit (20) and convert the speech into character information.
    • 4. 发明公开
    • SPEECH RECOGNITION DEVICE
    • SPRACHERKENNUNGSSYSTEM
    • EP1691344A1
    • 2006-08-16
    • EP04818533.4
    • 2004-11-12
    • HONDA MOTOR CO., Ltd.
    • NAKADAI, KazuhiroTSUJINO, HiroshiOKUNO, Hiroshi 1102, Form Higashi Toin SanjyoYAMAMOTO, Shunichi
    • G10L15/06
    • G10L15/20G10L21/028G10L2021/02166
    • An automatic speech recognition system includes: a sound source localization module for localizing a sound direction of a speaker based on the acoustic signals detected by the plurality of microphones; a sound source separation module for separating a speech signal of the speaker from the acoustic signals according to the sound direction; an acoustic model memory which stores direction-dependent acoustic models that are adjusted to a plurality of directions at intervals; an acoustic model composition module which composes an acoustic model adjusted to the sound direction, which is localized by the sound source localization module, based on the direction-dependent acoustic models, the acoustic model composition module storing the acoustic model in the acoustic model memory; and a speech recognition module which recognizes the features extracted by a feature extractor as character information using the acoustic model composed by the acoustic model composition module.
    • 一种自动语音识别系统,包括:声源定位模块,用于基于由所述多个麦克风检测到的声信号来定位扬声器的声音方向; 声源分离模块,用于根据声音方向将扬声器的语音信号与声学信号分离; 声学模型存储器,其存储以时间间隔调整到多个方向的方向相关的声学模型; 声学模型合成模块,其基于所述方向相关的声学模型,组合声学模型组合模块,所述声学模型组合模块将声学模型调整到声音方向,所述声学模型由所述声源定位模块定位,所述声学模型组合模块将所述声学模型存储在所述声学模型存储器中; 以及语音识别模块,其使用由声学模型组合模块组成的声学模型识别由特征提取器提取的特征作为字符信息。