公开(公告)号：US07302390B2

公开(公告)日：2007-11-27

申请号：US10338547

申请日：2003-01-08

申请人： Yin-Pin Yang ,  Po-Cheng Chen ,  Chien-Chieh Wang

发明人： Yin-Pin Yang ,  Po-Cheng Chen ,  Chien-Chieh Wang

IPC分类号： G10L15/00

CPC分类号： G10L15/30

摘要： A configurable distributed speech recognition system comprises a configurable distributed speech recognition protocol, and a configurable distributed speech recognition server. Herein, the configurable distributed speech recognition protocol is used to establish data transmitting format, for a client speech mobile device to packet the speech data and configuration data become a message packet. The configurable distributed speech recognition system receives the message packet from the client speech mobile device, configures its own speech recognition modules and resources according to the configuration data, and then returns a result to the client speech mobile device after completing the speech recognition.

摘要翻译： 可配置分布式语音识别系统包括可配置分布式语音识别协议和可配置分布式语音识别服务器。 这里，可配置分布式语音识别协议用于建立数据发送格式，对于客户端语音移动设备来分组语音数据，并且配置数据成为消息分组。 可配置分布式语音识别系统从客户端语音移动设备接收消息分组，根据配置数据配置自己的语音识别模块和资源，然后在完成语音识别之后将结果返回给客户端语音移动设备。

公开(公告)号：US07219057B2

公开(公告)日：2007-05-15

申请号：US11147951

申请日：2005-06-08

申请人： Yin-Pin Yang

发明人： Yin-Pin Yang

IPC分类号： G10L15/22

CPC分类号： G10L15/30 ,  G10L15/02 ,  G10L2015/228

摘要： A speech recognition method includes receiving signals derived from indices of a codebook corresponding to recognition feature vectors extracted from speech to be recognized. The signals include an indication of the number of bits per codebook index. The method also includes obtaining the string of indices from the received signals, obtaining the corresponding recognition feature vectors from the string of indices, and applying the recognition feature vectors to a word-level recognition process. To conserve network capacity, the size of the codebook and the corresponding number of bits per codebook index, are adapted on a dialogue-by-dialogue basis. The adaptation accomplishes a tradeoff between expected recognition rate and expected bitrate by optimizing a metric which is a function of both.

摘要翻译： 一种语音识别方法，包括接收从与将被识别的语音提取的识别特征向量对应的码本的索引得到的信号。 这些信号包括每个码本索引的位数的指示。 该方法还包括从接收到的信号获得索引串，从索引串获得相应的识别特征向量，并将识别特征向量应用于字级识别过程。 为了节省网络容量，码本的大小和每个码本索引的相应位数将在逐个对话的基础上进行调整。 适应通过优化作为两者的函数的度量来实现预期识别率和预期比特率之间的折衷。

公开(公告)号：US20050267753A1

公开(公告)日：2005-12-01

申请号：US11147951

申请日：2005-06-08

申请人： Yin-Pin Yang

发明人： Yin-Pin Yang

IPC分类号： G10L15/02 ,  G10L15/26 ,  G10L15/28 ,  G10L15/04

CPC分类号： G10L15/30 ,  G10L15/02 ,  G10L2015/228

摘要： In a mobile wireless communication system automatic speech recognition is performed in a distributed manner using a mobile station based near or front end stage which extracts and vector quantizes recognition feature parameters from frames of an utterance and an infrastructure based back or far end stage which reverses the vector quantization to recover the feature parameters and subjects the feature parameters to a Hidden Markov Model (HMM) evaluation to obtain a recognition decision for the utterance. In order to conserve network capacity, the size (Sz) of the codebook used for the vector quantization, and the corresponding number of bits (B) per codebook index B, are adapted on a dialogue-by-dialogue basis in relation to the vocabulary size |V| for the dialogue. The adaptation, which is performed at the front end, accomplishes a tradeoff between expected recognition rate RR and expected bitrate RR by optimizing a metric which is a function of both. In addition to the frame-wise compression of an utterance into a string of code indices (q-string), further “timewise” compression is obtained by run-length coding the string. The data transmitted from the front end to the back end includes the number of bits (B) per codebook value, which also indicates the codebook size (Sz).

摘要翻译： 在移动无线通信系统中，使用基于移动台的近端或前端阶段，以分布式方式执行自动语音识别，该移动台从话音和基于设施的后端或远端阶段的帧中提取和矢量量化识别特征参数， 矢量量化以恢复特征参数，并将特征参数进行隐马尔可夫模型（HMM）评估，以获得用于说话的识别决定。 为了节省网络容量，用于矢量量化的码本的大小（Sz）和每个码本索引B的相应位数（B）相对于词汇在逐个对话的基础上进行调整 尺寸| V | 为对话。 在前端执行的适应通过优化作为两者的函数的度量来实现预期识别率RR和预期比特率RR之间的折衷。 除了将语音逐帧压缩成一串码索引（q-string）之外，还通过对字符串进行游程编码来获得进一步的“时间”压缩。 从前端发送到后端的数据包括每个码本值的位数（B），其也表示码本大小（Sz）。

公开(公告)号：US06934678B1

公开(公告)日：2005-08-23

申请号：US09668541

申请日：2000-09-25

申请人： Yin-Pin Yang

发明人： Yin-Pin Yang

IPC分类号： G10L15/02 ,  G10L15/26 ,  G10L15/28 ,  G10L19/00

CPC分类号： G10L15/30 ,  G10L15/02 ,  G10L2015/228

摘要： In a mobile wireless communication system automatic speech recognition is performed in a distributed manner using a mobile station based near or front end stage which extracts and vector quantizes recognition feature parameters from frames of an utterance and an infrastructure based back or far end stage which reverses the vector quantization to recover the feature parameters and subjects the feature parameters to a Hidden Markov Model (HMM) evaluation to obtain a recognition decision for the utterance. In order to conserve network capacity, the size (Sz) of the codebook used for the vector quantization, and the corresponding number of bits (B) per codebook index B, are adapted on a dialogue-by dialogue basis in relation to the vocabulary size |V| for the dialogue. The adaptation is performed at the front end, accomplishes a tradeoff between expected recognition rate RR and expected bitrate BR by optimizing a metric which is a function of both.

摘要翻译： 在移动无线通信系统中，使用基于移动台的近端或前端阶段，以分布式方式执行自动语音识别，该移动台从话音和基于设施的后端或远端阶段的帧中提取和矢量量化识别特征参数， 矢量量化以恢复特征参数，并将特征参数进行隐马尔可夫模型（HMM）评估，以获得用于说话的识别决定。 为了节省网络容量，用于向量量化的码本的大小（Sz）和每个码本索引B的相应位数（B）相对于词汇大小在对话基础上进行调整 | V | 为对话。 在前端执行适配，通过优化作为两者的函数的度量来实现预期识别率RR和预期比特率BR之间的折衷。