利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

620 条记录 (耗时 0.021 秒)

    VOICE RECOGNITION METHOD, VOICE RECOGNITION DEVICE, AND ELECTRONIC DEVICE
    23.
    发明公开
    VOICE RECOGNITION METHOD, VOICE RECOGNITION DEVICE, AND ELECTRONIC DEVICE 审中-公开
    SPRACHERKENNUNGSVERFAHREN，SPRACHERKENNUNGSVORRICHTUNG ELEKTRONISCHE VORRICHTUNG

    公开(公告)号：EP2894449A1

    公开(公告)日：2015-07-15

    申请号：EP14812390.4

    申请日：2014-08-01

    申请人： Huawei Technologies Co., Ltd.

    发明人： ZHOU, Junyang

    IPC分类号： G01L15/00

    CPC分类号： G10L15/20 ,  G10L21/02 ,  G10L21/0216 ,  G10L21/0224 ,  H04R3/00

    摘要： The present invention discloses a voice recognition method, a voice recognition device, and an electronic device. In this method, first determining is performed by using a sample environment corresponding to a detection voice and a previous environment type, so as to output a corresponding voice correction instruction to a voice engine; then, a to-be-recognized voice is input to the voice engine and a noise type detection engine at the same time, and the voice engine corrects the to-be-recognized voice by using the voice correction instruction, so that quality of an original voice is not impaired by noise processing, and a corresponding initial recognition result is output; the noise type detection engine determines a current environment type by using the to-be-recognized voice and a voice training sample under a different environment; finally, confidence of the initial recognition result is adjusted by using the current environment type, so as to ensure that a recognition effect of a finally output voice recognition result can provide good user experience for a user under a current environment.

    摘要翻译： 本发明公开了一种语音识别方法，语音识别装置和电子装置。 在该方法中，通过使用与检测语音和先前环境类型对应的样本环境来执行第一确定，以便将语音校正指令输出到语音引擎; 然后，将被识别的语音同时输入到语音引擎和噪声类型检测引擎，并且语音引擎通过使用语音校正指令来校正被识别的语音，使得质量 原始声音不受噪声处理的影响，并输出相应的初始识别结果; 噪声型检测引擎通过在不同环境下使用被识别的语音和语音训练样本来确定当前的环境类型; 最后，通过使用当前环境类型来调整初始识别结果的置信度，以确保最终输出的语音识别结果的识别效果可以在当前环境下为用户提供良好的用户体验。

    SPEECH RECOGNITION APPARATUS AND METHOD
    24.
    发明公开
    SPEECH RECOGNITION APPARATUS AND METHOD 审中-公开
    语音识别设备和方法

    公开(公告)号：EP2871640A1

    公开(公告)日：2015-05-13

    申请号：EP13817278.8

    申请日：2013-07-05

    申请人： LG Electronics, Inc.

    发明人： JUNG, Dukyung

    IPC分类号： G10L15/28 ,  G10L15/24

    CPC分类号： G10L15/083 ,  G10L15/20 ,  G10L15/25 ,  G10L2015/227

    摘要： The present specification relates to a speech recognition apparatus and method capable of accurately recognizing the speech of a user in an easy and convenient manner without the user having to operate a speech recognition start button or the like. The speech recognition apparatus according to embodiments of the present specification comprises: a camera for capturing a user image; a microphone; a control unit for detecting a preset user gesture from the user image, and, if a nonlexical word is detected from the speech signal which is input through the microphone from the point in time at which the user gesture was detected, determining the speed signal detected after the detected nonlexical word as an effective speech signal; and a speech recognition unit for recognizing the effective speech signal.

    META-DATA INPUTS TO FRONT END PROCESSING FOR AUTOMATIC SPEECH RECOGNITION
    25.
    发明公开
    META-DATA INPUTS TO FRONT END PROCESSING FOR AUTOMATIC SPEECH RECOGNITION 有权
    METADATENEINGABEN BEI DER FRONTEND-VERARBEITUNGFÜRAUTOMATISCHE SPRACHERKENNUNG

    公开(公告)号：EP2867890A1

    公开(公告)日：2015-05-06

    申请号：EP12735984.2

    申请日：2012-06-28

    申请人： Nuance Communications, Inc.

    发明人： WILLETT, Daniel ,  LÖÖF, Karl, Jonas ,  PAN, Yue ,  PINTO, Joel ,  GOLLAN, Christian

    IPC分类号： G10L15/20 ,  G10L15/24 ,  G06F17/30

    CPC分类号： G10L15/14 ,  G10L15/02 ,  G10L15/20 ,  G10L25/30

    摘要： A computer-implemented method is described for front end speech processing for automatic speech recognition. A sequence of speech features which characterize an unknown speech input provided on an audio input channel and associated meta-data which characterize the audio input channel are received. The speech features are transformed with a computer process that uses a trained mapping function controlled by the meta-data, and automatic speech recognition is performed of the transformed speech features.

    摘要翻译： 描述了用于自动语音识别的前端语音处理的计算机实现的方法。 接收表征提供在音频输入通道上的未知语音输入和表征音频输入通道的相关联的元数据数据的语音特征序列。 通过使用由元数据控制的经过训练的映射函数的计算机处理来转换语音特征，并且对转换后的语音特征进行自动语音识别。

    Low power activation of a voice activated device
    28.
    发明公开
    Low power activation of a voice activated device 审中-公开
    Leistung einer sprachaktivierten Vorrichtung

    公开(公告)号：EP2801974A2

    公开(公告)日：2014-11-12

    申请号：EP14167581.9

    申请日：2014-05-08

    申请人： DSP Group Ltd.

    发明人： Haiut, Moshe ,  Heiman, Arie ,  Yehuday, Uri

    IPC分类号： G10L15/28

    CPC分类号： G10L15/20 ,  G06F1/3265 ,  G06F3/167 ,  G10L15/28 ,  G10L25/78

    摘要： In a mobile device, a bone conduction or vibration sensor is used to detect the user's speech and the resulting output is used as the source for a low power Voice Trigger (VT) circuit that can activate the Automatic Speech Recognition (ASR) of the host device. This invention is applicable to mobile devices such as wearable computers with head mounted display, mobile phones and wireless headsets and headphones which use speech recognition for the entering of input commands and control. The speech sensor can be a bone conduction microphone used to detect sound vibrations in the skull, or a vibration sensor, used to detect sound pressure vibrations from the user's speech. This VT circuit can be independent of any audio components of the host device and can therefore be designed to consume ultra-low power. Hence, this VT circuit can be active when the host device is in a sleeping state and can be used to wake the host device on detection of speech from the user. This VT circuit will be resistant to outside noise and react solely to the user's voice.

    摘要翻译： 在移动设备中，使用骨传导或振动传感器来检测用户的语音，并且所得到的输出被用作可以激活主机的自动语音识别（ASR）的低功率语音触发（VT）电路的源 设备。 本发明可应用于诸如具有头戴式显示器的可穿戴计算机，移动电话和无线耳机以及使用语音识别来输入输入命令和控制的耳机的移动设备。 语音传感器可以是用于检测颅骨中的声音振动的骨传导麦克风或用于检测来自用户的语音的声压振动的振动传感器。 该VT电路可以独立于主机设备的任何音频组件，因此可以被设计为消耗超低功耗。 因此，当主机设备处于睡眠状态时，该VT电路可以是活动的，并且可以用于在从用户检测到语音时唤醒主机设备。 该VT电路将抵抗外部噪声，并仅对使用者的声音作出反应。

    Voice processing apparatus and voice processing method
    29.
    发明公开
    Voice processing apparatus and voice processing method 审中-公开
    Sprachverarbeitungsvorrichtung und Sprachverarbeitungsverfahren

    公开(公告)号：EP2797077A1

    公开(公告)日：2014-10-29

    申请号：EP13188757.2

    申请日：2013-10-15

    申请人： Samsung Electronics Co., Ltd

    发明人： Kim, Sang-jin ,  Yun, Hyun-kyu

    IPC分类号： G10L15/22 ,  G10L21/02 ,  G10L15/26

    CPC分类号： G10L15/20 ,  G10L15/30 ,  G10L21/02 ,  G10L2015/221 ,  G10L2015/228 ,  H04N5/4403 ,  H04N21/23418 ,  H04N21/42203 ,  H04N21/4221 ,  H04N21/43637 ,  H04N21/439 ,  H04N21/6582

    摘要： A voice processing apparatus includes: a voice receptor configured to collect a user voice, convert the user voice into a first voice signal, and to output the first voice signal; an audio processor configured to process a sound output through a speaker to output an audio signal; a memory unit configured to store the first voice signal output from the voice receptor and the audio signal output from the audio processor; an echo canceller configured to remove an echo from the first voice signal to generate a second voice signal; and a first controller configured to control the echo canceller to generate the second voice signal based on the first voice signal and the audio signal stored in the memory unit.

    摘要翻译： 语音处理装置包括：语音接收器，被配置为收集用户语音，将用户语音转换为第一语音信号，并输出第一语音信号; 音频处理器，被配置为处理通过扬声器的声音输出以输出音频信号; 存储单元，被配置为存储从语音接收器输出的第一语音信号和从音频处理器输出的音频信号; 回波消除器，被配置为从所述第一语音信号中去除回声以产生第二语音信号; 以及第一控制器，被配置为基于存储在存储器单元中的第一语音信号和音频信号来控制回声消除器以产生第二语音信号。

    CONTEXT-BASED SMARTPHONE SENSOR LOGIC
    30.
    发明公开
    CONTEXT-BASED SMARTPHONE SENSOR LOGIC 审中-公开
    基于上下文的SMARTPHONE传感器逻辑

    公开(公告)号：EP2758956A1

    公开(公告)日：2014-07-30

    申请号：EP12833294.7

    申请日：2012-09-07

    申请人： Digimarc Corporation

    发明人： RODRIGUEZ, Tony, F. ,  BAI, Yang

    IPC分类号： G10L15/00

    CPC分类号： G10L15/285 ,  G06K9/00006 ,  G06K9/00013 ,  G06K9/00228 ,  G06K9/00892 ,  G06K9/6267 ,  G06T7/00 ,  G10L15/08 ,  G10L15/20 ,  G10L15/22 ,  G10L19/00 ,  G10L2015/226 ,  H04M1/72569 ,  H04M2250/12

    摘要： Methods employ sensors in portable devices (e.g., smartphones) both to sense content information (e.g., audio and imagery) and context information. Device processing is desirably dependent on both. For example, some embodiments activate certain processor intensive operations (e.g., content recognition) based on classification of sensed content and context. The context can control the location where information produced from such operations is stored, or control an alert signal indicating, e.g., that sensed speech is being transcribed. Some arrangements post sensor data collected by one device to a cloud repository, for access and processing by other devices. Multiple devices can collaborate in collecting and processing data, to exploit advantages each may have (e.g., in location, processing ability, social network resources, etc.). A great many other features and arrangements are also detailed.