公开(公告)号：EP0549265A3

公开(公告)日：1994-01-26

申请号：EP92311549.7

申请日：1992-12-17

Applicant: Oregon Graduate Institute of Science and Technology

Inventor： Cole, Ronald A. ,  Fanty, Mark A.

IPC: G10L9/00

CPC classification number: G10L15/16

Abstract: Improved system and method for speaker-independent speech token recognition are described. The system is neural network-based and involves processing a sequence of spoken utterance, e.g. separately articulated letters of a name, to identify the same based upon a highest probability match of each utterance with learned speech tokens, e.g. the letters of the English language alphabet, and based upon a highest probability match of the uttered sequence with a defined utterance library, e.g. a list of names. First, the spoken utterance is digitized or captured and processed into a spectral representation. Second, discrete time frames of the spectral representation are classified phonetically using the spectral coefficients. Third, the time-frame outputs are used by a modified Viterbi search to locate segment boundaries, near which such segment boundaries lies the information that is needed to discriminate letters. Fourth, the segmented or bounded representation is reclassified using such information into individual hypothesized letters. Fifth, successive, hypothesized letter scores are analyzed to obtain a high probability match with a spelled word within the utterance library. The system and method comprehend finer distinctions near points of interest used to discriminate difficult-to-recognize letter pair differences such as M/N, B/D, etc.. The system is described in the context of phone line reception of names spelled by remote users.

Abstract translation: 描述了用于说话者无关的话音标记识别的改进的系统和方法。 该系统是基于神经网络的并且涉及处理一系列说出的话语，例如， 分开表达姓名的字母，以基于每个话语与学习的语音令牌的最高概率匹配来识别它，例如， 英语字母表的字母，并且基于发音序列与定义的话语库的最高概率匹配，例如， 名单列表。 首先，将所说话语数字化或捕获并处理成频谱表示。 其次，频谱表示的离散时间帧使用频谱系数进行发音分类。 第三，时间帧输出由改进的维特比搜索使用以定位分段边界，在该边界附近，这样的分段边界是区分字母所需的信息。 第四，使用这种信息将分段或有界的表示重新分类为单个虚拟字母。 第五，分析连续的假设字母分数以获得与话语库内的拼写单词的高概率匹配。 该系统和方法理解用于区分诸如M / N，B / D等难以识别的字母对差异的兴趣点附近的更细微的区别。该系统在电话线接收名称拼写为 远程用户。

公开(公告)号：EP0549265A2

公开(公告)日：1993-06-30

申请号：EP92311549.7

申请日：1992-12-17

Applicant: Oregon Graduate Institute of Science and Technology

Inventor： Cole, Ronald A. ,  Fanty, Mark A.

IPC: G10L9/00

CPC classification number: G10L15/16

Abstract: Improved system and method for speaker-independent speech token recognition are described. The system is neural network-based and involves processing a sequence of spoken utterance, e.g. separately articulated letters of a name, to identify the same based upon a highest probability match of each utterance with learned speech tokens, e.g. the letters of the English language alphabet, and based upon a highest probability match of the uttered sequence with a defined utterance library, e.g. a list of names. First, the spoken utterance is digitized or captured and processed into a spectral representation. Second, discrete time frames of the spectral representation are classified phonetically using the spectral coefficients. Third, the time-frame outputs are used by a modified Viterbi search to locate segment boundaries, near which such segment boundaries lies the information that is needed to discriminate letters. Fourth, the segmented or bounded representation is reclassified using such information into individual hypothesized letters. Fifth, successive, hypothesized letter scores are analyzed to obtain a high probability match with a spelled word within the utterance library. The system and method comprehend finer distinctions near points of interest used to discriminate difficult-to-recognize letter pair differences such as M/N, B/D, etc.. The system is described in the context of phone line reception of names spelled by remote users.

Abstract translation: 描述了与讲话者无关的语音令牌识别的改进的系统和方法。 该系统是基于神经网络的，涉及处理一系列口头发音，例如， 根据每个话语与所学习的语音令牌的最高概率匹配来识别相同的名称的单独的关联字母，例如。 英文字母的字母，并且基于所发出的序列与定义的话语库的最高概率匹配，例如， 名单清单。 首先，口头发音被数字化或被捕获并处理成频谱表示。 第二，频谱表示的离散时间帧使用频谱系数进行语音分类。 第三，时间帧输出被修改的维特比搜索用于定位分段边界，其中这些分段边界位于识别字母所需的信息附近。 第四，分段或有界的表示使用这些信息重新分类为个人假设的信件。 第五，分析连续的，假设的字母得分，以获得与发音库内的拼写单词的高概率匹配。 该系统和方法理解用于区分难以识别的字母对差异（例如M / N，B / D等）的感兴趣点附近的更好的区别。该系统在电话线接收的上下文中被描述，其名称由 远程用户。