公开(公告)号：US08296141B2

公开(公告)日：2012-10-23

申请号：US12274025

申请日：2008-11-19

申请人： Mazin Gilbert ,  Alistair D. Conkie ,  Andrej Ljolje

发明人： Mazin Gilbert ,  Alistair D. Conkie ,  Andrej Ljolje

IPC分类号： G10L15/04

CPC分类号： G10L15/063 ,  G10L2015/025

摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable media for speech recognition. The method includes receiving speech utterances, assigning a pronunciation weight to each unit of speech in the speech utterances, each respective pronunciation weight being normalized at a unit of speech level to sum to 1, for each received speech utterance, optimizing the pronunciation weight by (1) identifying word and phone alignments and corresponding likelihood scores, and (2) discriminatively adapting the pronunciation weight to minimize classification errors, and recognizing additional received speech utterances using the optimized pronunciation weights. A unit of speech can be a sentence, a word, a context-dependent phone, a context-independent phone, or a syllable. The method can further include discriminatively adapting pronunciation weights based on an objective function. The objective function can be maximum mutual information (MMI), maximum likelihood (MLE) training, minimum classification error (MCE) training, or other functions known to those of skill in the art. Speech utterances can be names. The speech utterances can be received as part of a multimodal search or input. The step of discriminatively adapting pronunciation weights can further include stochastically modeling pronunciations.

摘要翻译： 本文公开了用于语音识别的系统，计算机实现的方法和计算机可读介质。 该方法包括接收语音话语，在语音话语中为每个语音单元分配发音权重，将每个相应的发音权重以语音级别为单位归一化为1，对于每个接收到的语音话语，通过（ 1）识别词和电话对齐和相应的可能性分数，以及（2）歧视地调整发音权重以最小化分类错误，以及使用优化的发音权重来识别附加的接收到的语音话语。 语音单位可以是句子，单词，上下文相关的电话，与上下文无关的电话或音节。 该方法还可以包括基于目标函数的歧视地适应发音权重。 目标函数可以是本领域技术人员已知的最大相互信息（MMI），最大似然（MLE）训练，最小分类误差（MCE）训练或其他功能。 言语言可以是名字。 可以作为多模态搜索或输入的一部分接收演讲话语。 歧视性地适应发音权重的步骤还可以包括随机建模发音。

公开(公告)号：US20120078617A1

公开(公告)日：2012-03-29

申请号：US13311512

申请日：2011-12-05

申请人： Alistair D. Conkie ,  Mazin Gilbert ,  Andrej Ljolje

发明人： Alistair D. Conkie ,  Mazin Gilbert ,  Andrej Ljolje

IPC分类号： G06F17/21

CPC分类号： G06F17/277 ,  G10L15/063 ,  G10L15/187

摘要： The present disclosure relates to systems, methods, and computer-readable media for generating a lexicon for use with speech recognition. The method includes receiving symbolic input as labeled speech data, overgenerating potential pronunciations based on the symbolic input, identifying potential pronunciations in a speech recognition context, and storing the identified potential pronunciations in a lexicon. Overgenerating potential pronunciations can include establishing a set of conversion rules for short sequences of letters, converting portions of the symbolic input into a number of possible lexical pronunciation variants based on the set of conversion rules, modeling the possible lexical pronunciation variants in one of a weighted network and a list of phoneme lists, and iteratively retraining the set of conversion rules based on improved pronunciations. Symbolic input can include multiple examples of a same spoken word. Speech data can be labeled explicitly or implicitly and can include words as text and recorded audio.

摘要翻译： 本公开涉及用于生成用于语音识别的词典的系统，方法和计算机可读介质。 所述方法包括：将符号输入作为标记的语音数据接收，基于所述符号输入过度生成潜在发音，识别语音识别语境中的潜在发音，以及将所识别的潜在发音存储在词典中。 过度生成潜在发音可以包括为短的字母序列建立一组转换规则，基于一组转换规则将符号输入的部分转换成许多可能的词汇发音变体，对可能的词汇发音变体在加权 网络和音素列表，并且基于改进的发音迭代地重新训练一组转换规则。 符号输入可以包括相同口语单词的多个示例。 语音数据可以被明确地或隐含地标记，并且可以将单词包括为文本和记录的音频。

公开(公告)号：US20120065975A1

公开(公告)日：2012-03-15

申请号：US13302380

申请日：2011-11-22

申请人： Andrej Ljolje ,  Alistair D. Conkie ,  Ann K. Syrdal

发明人： Andrej Ljolje ,  Alistair D. Conkie ,  Ann K. Syrdal

IPC分类号： G10L15/04

CPC分类号： G10L15/187 ,  G10L15/183 ,  G10L2015/025

摘要： Systems, computer-implemented methods, and tangible computer-readable media for generating a pronunciation model. The method includes identifying a generic model of speech composed of phonemes, identifying a family of interchangeable phonemic alternatives for a phoneme in the generic model of speech, labeling the family of interchangeable phonemic alternatives as referring to the same phoneme, and generating a pronunciation model which substitutes each family for each respective phoneme. In one aspect, the generic model of speech is a vocal tract length normalized acoustic model. Interchangeable phonemic alternatives can represent a same phoneme for different dialectal classes. An interchangeable phonemic alternative can include a string of phonemes.

摘要翻译： 系统，计算机实现的方法和用于生成发音模型的有形计算机可读介质。 该方法包括识别由音素组成的通用语音模型，在通用语音模型中识别音素的可互换音素替代品系列，将可互换音素替代品的家族标记为指相同的音素，以及生成发音模型，其中 将每个家庭的每个音素替代。 在一个方面，语音的通用模型是声道长度归一化声学模型。 可互换的音素替代品可以代表不同方言课程的相同音素。 可互换的音素替代品可以包括一串音素。

公开(公告)号：US08095365B2

公开(公告)日：2012-01-10

申请号：US12328436

申请日：2008-12-04

申请人： Alistair D. Conkie ,  Mazin Gilbert ,  Andrej Ljolje

发明人： Alistair D. Conkie ,  Mazin Gilbert ,  Andrej Ljolje

IPC分类号： G10L13/08

CPC分类号： G06F17/277 ,  G10L15/063 ,  G10L15/187

摘要： The present disclosure relates to systems, methods, and computer-readable media for generating a lexicon for use with speech recognition. The method includes receiving symbolic input as labeled speech data, overgenerating potential pronunciations based on the symbolic input, identifying potential pronunciations in a speech recognition context, and storing the identified potential pronunciations in a lexicon. Overgenerating potential pronunciations can include establishing a set of conversion rules for short sequences of letters, converting portions of the symbolic input into a number of possible lexical pronunciation variants based on the set of conversion rules, modeling the possible lexical pronunciation variants in one of a weighted network and a list of phoneme lists, and iteratively retraining the set of conversion rules based on improved pronunciations. Symbolic input can include multiple examples of a same spoken word. Speech data can be labeled explicitly or implicitly and can include words as text and recorded audio.

摘要翻译： 本公开涉及用于生成用于语音识别的词典的系统，方法和计算机可读介质。 所述方法包括：将符号输入作为标记的语音数据接收，基于所述符号输入过度生成潜在发音，识别语音识别语境中的潜在发音，以及将所识别的潜在发音存储在词典中。 过度生成潜在发音可以包括为短的字母序列建立一组转换规则，基于一组转换规则将符号输入的部分转换成许多可能的词汇发音变体，对可能的词汇发音变体在加权 网络和音素列表，并且基于改进的发音迭代地重新训练一组转换规则。 符号输入可以包括相同口语单词的多个示例。 语音数据可以被明确地或隐含地标记，并且可以将单词包括为文本和记录的音频。

公开(公告)号：US07567903B1

公开(公告)日：2009-07-28

申请号：US11034535

申请日：2005-01-12

申请人： Vincent Goffin ,  Andrej Ljolje ,  Murat Saraclar

发明人： Vincent Goffin ,  Andrej Ljolje ,  Murat Saraclar

IPC分类号： G10L15/06 ,  G10L15/10 ,  G10L17/00 ,  G10L13/00 ,  G10L19/14

CPC分类号： G10L15/063 ,  G10L15/10 ,  G10L15/12 ,  G10L17/04 ,  G10L17/08

摘要： A method and apparatus for performing speech recognition are provided. A Vocal Tract Length Normalized acoustic model for a speaker is generated from training data. Speech recognition is performed on a first recognition input to determine a first best hypothesis. A first Vocal Tract Length Normalization factor is estimated based on the first best hypothesis. Speech recognition is performed on a second recognition input using the Vocal Tract Length Normalized acoustic model to determine an other best hypothesis. An other Vocal Tract Length Normalization factor is estimated based on the other best hypothesis and at least one previous best hypothesis.

摘要翻译： 提供了一种用于执行语音识别的方法和装置。 声音段长度从训练数据生成扬声器的归一化声学模型。 在第一识别输入上执行语音识别以确定第一最佳假设。 第一个声带长度归一化因子是基于第一个最佳假设估计的。 在第二识别输入上使用声带长度归一化声学模型进行语音识别，以确定另一个最佳假设。 另一个声带长度归一化因子基于另一个最佳假设和至少一个先前的最佳假设来估计。