-
1.发明申请Method and apparatus for generating and displaying N-Best alternatives in a speech recognition system 有权用于在语音识别系统中生成和显示N-Best替代的方法和装置公开(公告)号：US20050091054A1
公开(公告)日：2005-04-28
申请号：US10996317
申请日：2004-11-23
申请人： Chris Thrasher , Fileno Alleva
发明人： Chris Thrasher , Fileno Alleva
IPC分类号： G06F9/44 , G10L15/08 , G10L15/18 , G10L15/22 , G10L15/26 , G10L15/28 , H04L29/06 , H04L29/08 , G10L15/00
CPC分类号： G10L15/28 , G06F9/4488 , G10L15/083 , G10L15/197 , G10L15/26 , H04L29/06027
摘要： The present invention is directed to a method and apparatus for generating alternatives to words indicative of recognized speech. A reference path of recognized words is generated, based upon input speech data. An operator selection input is received and is indicative of a selected portion of the recognized speech, for which alternatives are to be generated. Boundary conditions for alternatives to be generated are calculated based upon bounds of a reference subpath corresponding to the selected portion of the recognized speech. Alternate subpaths satisfying the boundary conditions are constructed from a hypothesis store which corresponds to the input speech data.
摘要翻译： 本发明涉及一种用于产生替代指示识别的语音的单词的方法和装置。 基于输入的语音数据生成识别字的参考路径。 接收到操作者选择输入并且指示所识别的语音的选定部分，为此生成替代方案。 基于与识别的语音的所选部分相对应的参考子路径的边界来计算用于生成替代物的边界条件。 满足边界条件的备用子路径由对应于输入语音数据的假设存储器构成。
-
公开(公告)号：US20050071162A1
公开(公告)日：2005-03-31
申请号：US10987529
申请日：2004-11-12
CPC分类号： G10L15/065
摘要： An unsupervised adaptation method and apparatus are provided that reduce the storage and time requirements associated with adaptation. Under the invention, utterances are converted into feature vectors, which are decoded to produce a transcript and alignment unit boundaries for the utterance. Individual alignment units and the feature vectors associated with those alignment units are then provided to an alignment function, which aligns the feature vectors with the states of each alignment unit. Because the alignment is performed within alignment unit boundaries, fewer feature vectors are used and the time for alignment is reduced. After alignment, the feature vector dimensions aligned to a state are added to dimension sums that are kept for that state. After all the states in an utterance have had their sums updated, the speech signal and the alignment units are deleted. Once sufficient frames of data have been received to perform adaptive training, the acoustic model is adapted.
-
公开(公告)号：US07251600B2
公开(公告)日：2007-07-31
申请号：US11092252
申请日：2005-03-29
申请人： Yun-cheng Ju , Fileno Alleva
发明人： Yun-cheng Ju , Fileno Alleva
IPC分类号： G10L15/18
CPC分类号： G10L15/18 , G10L15/063
摘要： A language model for a language processing system such as a speech recognition system is constructed from training corpus formed from associated characters, word phrases and context cues. A method and apparatus for generating the training corpus used to train the language model and a system or module using such a language model is disclosed.
摘要翻译： 用于语言处理系统的语言模型如语音识别系统由从相关联的字符，单词和语境提示形成的训练语料库构建。 公开了一种用于生成用于训练语言模型的训练语料库和使用这种语言模型的系统或模块的方法和装置。
-
4.发明申请Method and apparatus for constructing and using syllable-like unit language models 有权用于构建和使用音节类单位语言模型的方法和装置公开(公告)号：US20050187769A1
公开(公告)日：2005-08-25
申请号：US11110602
申请日：2005-04-20
申请人： Mei-Yuh Hwang , Fileno Alleva , Rebecca Weiss
发明人： Mei-Yuh Hwang , Fileno Alleva , Rebecca Weiss
CPC分类号： G10L15/063 , G10L2015/0636
摘要： A method and computer-readable medium use syllable-like units (SLUs) to decode a pronunciation into a phonetic description. The syllable-like units are generally larger than a single phoneme but smaller than a word. The present invention provides a means for defining these syllable-like units and for generating a language model based on these syllable-like units that can be used in the decoding process. As SLUs are longer than phonemes, they contain more acoustic contextual clues and better lexical constraints for speech recognition. Thus, the phoneme accuracy produced from SLU recognition is much better than all-phone sequence recognition.
摘要翻译： 一种方法和计算机可读介质使用音节类单位（SLU）来将发音解码成语音描述。 音节式单元通常大于单个音素，但小于一个单词。 本发明提供了一种用于定义这些音节单元并且用于基于这些可以在解码过程中使用的音节单元来生成语言模型的装置。 由于SLU比音素长，它们包含更多的声学语境线索和语音识别的更好的词汇约束。 因此，从SLU识别产生的音素精度比全电话序列识别好得多。
-
公开(公告)号：US20050171761A1
公开(公告)日：2005-08-04
申请号：US11092252
申请日：2005-03-29
申请人： Yun-cheng Ju , Fileno Alleva
发明人： Yun-cheng Ju , Fileno Alleva
CPC分类号： G10L15/18 , G10L15/063
摘要： A language model for a language processing system such as a speech recognition system is constructed from training corpus formed from associated characters, word phrases and context cues. A method and apparatus for generating the training corpus used to train the language model and a system or module using such a language model is disclosed.
摘要翻译： 用于语言处理系统的语言模型如语音识别系统由从相关联的字符，单词和语境提示形成的训练语料库构建。 公开了一种用于生成用于训练语言模型的训练语料库和使用这种语言模型的系统或模块的方法和装置。
-
-
-
-
搜索结果
5 条记录 (耗时 0.011 秒)
