专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06789062B1 Automatically retraining a speech recognition system 有权
标题翻译：自动重新培训语音识别系统
公开(公告)号：US06789062B1
公开(公告)日：2004-09-07
申请号：US09512785
申请日：2000-02-25
申请人： Michael S. Phillips , Krishna K. Govindarajan , Mark Fanty , Etienne Barnard
发明人： Michael S. Phillips , Krishna K. Govindarajan , Mark Fanty , Etienne Barnard
IPC分类号： G01L1506
CPC分类号： G10L15/063 , G10L2015/0635
摘要： A telephone-based interactive speech recognition system is retrained using variable weighting and incremental retraining. Variable weighting involves changing the relative influence of particular measurement data to be reflected in a statistical model. Statistical model data is determined based upon an initial set of measurement data determined from an initial set of speech utterances. When new statistical model data is to be generated to reflect new measurement data determined from new speech utterances, a weighting factor is applied to the new measurement data to generate weighted new measurement data. The new statistical model data is then determined based upon the initial set of measurement data and the weighted new measurement data. Incremental retraining involves generating new statistical model data using prior statistical model data to reduce the amount of prior measurement data that must be maintained and processed. When prior statistical model data needs to be updated to reflect characteristics and attributes of new speech utterances, statistical model data is generated for the new speech utterances. Then the prior statistical model data and the statistical model data for the new measurement data are processed to generate the new statistical model data.
摘要翻译：基于电话的交互式语音识别系统使用可变加权和增量再培训进行再培训。可变权重涉及改变特定测量数据的相对影响，反映在统计模型中。基于从初始语音话语集确定的初始测量数据集来确定统计模型数据。当要生成新的统计模型数据以反映从新的语音话语确定的新的测量数据时，将加权因子应用于新的测量数据以产生加权的新的测量数据。然后基于测量数据的初始集合和加权的新测量数据来确定新的统计模型数据。增量再培训涉及使用先前的统计模型数据生成新的统计模型数据，以减少必须维护和处理的先前测量数据的数量。当先前的统计模型数据需要更新以反映新的语音话语的特征和属性时，会为新的语音语音产生统计模型数据。然后对先前的统计模型数据和新测量数据的统计模型数据进行处理，生成新的统计模型数据。

2. 发明授权

US06629073B1 Speech recognition method and apparatus utilizing multi-unit models 有权
标题翻译：使用多单元模型的语音识别方法和装置
公开(公告)号：US06629073B1
公开(公告)日：2003-09-30
申请号：US09559505
申请日：2000-04-27
申请人： Hsiao-Wuen Hon , Kuansan Wang
发明人： Hsiao-Wuen Hon , Kuansan Wang
IPC分类号： G01L1506
CPC分类号： G10L15/187 , G10L2015/022 , G10L2015/025
摘要： A speech recognition method and system utilize an acoustic model that is capable of providing probabilities for both a large acoustic unit and an acoustic sub-unit. Each of these probabilities describes the likelihood of a set of feature vectors from a series of feature vectors representing a speech signal. The large acoustic unit is formed from a plurality of acoustic sub-units. At least one sub-unit probability and at least on large unit probability from the acoustic model are used by a decoder to generate a score for a sequence of hypothesized words. When combined, the acoustic sub-units associated with all of the sub-unit probabilities used to determine the score span fewer than all of the feature vectors in the series of feature vectors. An overlapping decoding technique is also provided.
摘要翻译：语音识别方法和系统利用能够为大声学单元和声学子单元提供概率的声学模型。这些概率中的每一个描述了来自表示语音信号的一系列特征向量的一组特征向量的可能性。大型声学单元由多个声学子单元形成。解码器使用来自声学模型的至少一个子单元概率和至少基于大的单位概率来为假设词的序列生成分数。当组合时，与用于确定分数的所有子单元概率相关联的声学子单元小于该系列特征向量中的所有特征向量。还提供了重叠的解码技术。

3. 发明授权

US06708151B1 Reference pattern generating apparatus and method, and computer readable medium having reference pattern generating program embodied thereon 失效
标题翻译：参考图案生成装置和方法以及其上具有参考图案生成程序的计算机可读介质
公开(公告)号：US06708151B1
公开(公告)日：2004-03-16
申请号：US09660478
申请日：2000-09-12
申请人： Toshiyuki Hanazawa
发明人： Toshiyuki Hanazawa
IPC分类号： G01L1506
CPC分类号： G10L15/063 , G10L15/12 , G10L2015/0631
摘要： A reference pattern generating apparatus comprises an initial reference pattern generating unit for dividing a time series of feature vectors obtained from a voice signal into a sequence of small sections in such a manner that any two adjacent small sections overlap each other, and for averaging part of the time series of feature vectors included in each of the plurality of small sections so as to generate an initial reference pattern having a plurality of states respectively associated with the plurality of small sections. A reference pattern generating unit brings each of the plurality of states of the initial reference pattern into correspondence with part of the time series of feature vectors using pattern matching, and then averages the part of the time series of feature vectors brought into correspondence with each of the plurality of states of the initial reference pattern so as to update the initial reference pattern to generate a reference pattern.
摘要翻译：参考图案生成装置包括：初始参考图形生成单元，用于将从语音信号获得的特征向量的时间序列划分成小部分的序列，使得任意两个相邻的小部分彼此重叠，并且用于平均部分包括在所述多个小部分中的每一个中的特征向量的时间序列，以便生成具有分别与所述多个小部分相关联的多个状态的初始参考图案。参考图案生成单元使用图案匹配将初始参考图案的多个状态中的每一个与特征向量的时间序列的一部分对应，然后将与每个特征向量相对应的特征向量的时间序列的一部分平均化初始参考图案的多个状态，以便更新初始参考图案以生成参考图案。

4. 发明授权

US06366886B1 System and method for providing remote automatic speech recognition services via a packet network 有权
标题翻译：用于通过分组网络提供远程自动语音识别服务的系统和方法
公开(公告)号：US06366886B1
公开(公告)日：2002-04-02
申请号：US09533820
申请日：2000-03-24
申请人： Pamela Leigh Dragosh , David Bjorn Roe , Robert Douglas Sharp
发明人： Pamela Leigh Dragosh , David Bjorn Roe , Robert Douglas Sharp
IPC分类号： G01L1506
CPC分类号： G10L15/30 , H04M3/493 , H04M3/4936 , H04M7/006 , Y10S707/99945 , Y10S707/99948
摘要： A system and method of operating an automatic speech recognition service using a client-server architecture is used to make ASR services accessible at a client location remote from the location of the main ASR engine. The present invention utilizes client-server communications over a packet network, such as the Internet, where the ASR server receives a grammar from the client, receives information representing speech from the client, performs speech recognition, and returns information based upon the recognized speech to the client.
摘要翻译：使用使用客户端 - 服务器架构来操作自动语音识别服务的系统和方法用于使ASR服务在远离主ASR引擎的位置的客户端位置可访问。本发明通过诸如因特网的分组网络利用客户端 - 服务器通信，其中ASR服务器从客户端接收语法，从客户端接收表示语音的信息，执行语音识别，并且基于所识别的语音返回信息客户端。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式