公开(公告)号：EP3078020B1

公开(公告)日：2018-02-14

申请号：EP14824209.2

申请日：2014-12-05

申请人： Nuance Communications, Inc.

发明人： TANG, Yun ,  NAGESHA, Venkatesh ,  FAN, Xing

IPC分类号： G10L15/02 ,  G10L15/16 ,  G10L15/07 ,  G10L15/06

CPC分类号： G10L15/16 ,  G10L15/02 ,  G10L15/063 ,  G10L15/07 ,  G10L2015/025

摘要： In a speech recognition system, deep neural networks (DNNs) are employed in phoneme recognition. While DNNs typically provide better phoneme recognition performance than other techniques, such as Gaussian mixture models (GMM), adapting a DNN to a particular speaker is a real challenge. According to at least one example embodiment, speech data and corresponding speaker data are both applied as input to a DNN. In response, the DNN generates a prediction of a phoneme based on the input speech data and the corresponding speaker data. The speaker data may be generated from the corresponding speech data.

公开(公告)号：EP3078020A1

公开(公告)日：2016-10-12

申请号：EP14824209.2

申请日：2014-12-05

申请人： Nuance Communications, Inc.

发明人： TANG, Yun ,  NAGESHA, Venkatesh ,  FAN, Xing

IPC分类号： G10L15/16 ,  G10L15/07 ,  G10L15/06

CPC分类号： G10L15/16 ,  G10L15/02 ,  G10L15/063 ,  G10L15/07 ,  G10L2015/025

摘要： In a speech recognition system, deep neural networks (DNNs) are employed in phoneme recognition. While DNNs typically provide better phoneme recognition performance than other techniques, such as Gaussian mixture models (GMM), adapting a DNN to a particular speaker is a real challenge. According to at least one example embodiment, speech data and corresponding speaker data are both applied as input to a DNN. In response, the DNN generates a prediction of a phoneme based on the input speech data and the corresponding speaker data. The speaker data may be generated from the corresponding speech data.

摘要翻译： 在一个语音识别系统，深神经网络（DNNs）在音素识别中采用。 虽然DNNs通常提供比其他技术，颜色越好音素识别性能：如高斯混合模型（GMM）适应一个DNN到特定说话者是一个真正的挑战。 。根据至少一个示例实施例，语音数据和相应的扬声器数据都被作为输入施加到一个DNN。 作为响应，DNN基因费率基于所述输入的语音数据和数据对应的扬声器的音素的预测。 扬声器数据可以由相应的语音数据来生成。