公开(公告)号：US20160329045A1

公开(公告)日：2016-11-10

申请号：US15212908

申请日：2016-07-18

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Mazin GILBERT ,  Vincent GOFFIN ,  Taniya Mishra

IPC分类号： G10L15/06 ,  G10L15/01 ,  G10L15/18 ,  G10L15/26

CPC分类号： G10L15/063 ,  G10L15/01 ,  G10L15/18 ,  G10L15/26 ,  G10L2015/0635

摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for assigning saliency weights to words of an ASR model. The saliency values assigned to words within an ASR model are based on human perception judgments of previous transcripts. These saliency values are applied as weights to modify an ASR model such that the results of the weighted ASR model in converting a spoken document to a transcript provide a more accurate and useful transcription to the user.

公开(公告)号：US20150073797A1

公开(公告)日：2015-03-12

申请号：US14539221

申请日：2014-11-12

申请人： AT&T Intellectual Property I, L.P.

发明人： Alistair D. CONKIE ,  Mazin GILBERT ,  Andrej LJOLJE

IPC分类号： G06F17/27 ,  G10L15/06

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 overgenerating potential pronunciations based on 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。 该方法包括基于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：US20150006179A1

公开(公告)日：2015-01-01

申请号：US14488844

申请日：2014-09-17

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Alistair D. CONKIE ,  Ann K. SYRDAL

IPC分类号： G10L15/187

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：US20140288937A1

公开(公告)日：2014-09-25

申请号：US14299745

申请日：2014-06-09

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Alistair D. CONKIE

IPC分类号： G10L15/18

CPC分类号： G10L15/1815 ,  G06F17/27 ,  G10L13/027 ,  G10L15/02 ,  G10L15/04 ,  G10L15/20 ,  G10L25/87 ,  G10L2015/025

摘要： Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for handling missing speech data. The computer-implemented method includes receiving speech with a missing segment, generating a plurality of hypotheses for the missing segment, identifying a best hypothesis for the missing segment, and recognizing the received speech by inserting the identified best hypothesis for the missing segment. In another method embodiment, the final step is replaced with synthesizing the received speech by inserting the identified best hypothesis for the missing segment. In one aspect, the method further includes identifying a duration for the missing segment and generating the plurality of hypotheses of the identified duration for the missing segment. The step of identifying the best hypothesis for the missing segment can be based on speech context, a pronouncing lexicon, and/or a language model. Each hypothesis can have an identical acoustic score.

摘要翻译： 本文公开了用于处理丢失的语音数据的系统，计算机实现的方法和有形的计算机可读介质。 计算机实现的方法包括接收具有缺失段的语音，为缺失段生成多个假设，识别缺失段的最佳假设，以及通过为缺失段插入所识别的最佳假设来识别接收到的语音。 在另一种方法实施例中，通过为缺失的段插入所识别的最佳假设，来代替最后的步骤来合成所接收的语音。 在一个方面，所述方法还包括识别缺失段的持续时间并为缺失段生成所识别的持续时间的多个假设。 识别缺失片段的最佳假设的步骤可以基于语音上下文，发音词典和/或语言模型。 每个假设可以具有相同的声学得分。

公开(公告)号：US20150149162A1

公开(公告)日：2015-05-28

申请号：US14087885

申请日：2013-11-22

申请人： AT&T Intellectual Property I, L.P.

发明人： Ilya Dan MELAMED ,  Andrej LJOLJE

IPC分类号： G10L15/00

CPC分类号： G10L15/07 ,  G10L15/20 ,  G10L15/28 ,  G10L2015/227

摘要： Disclosed herein are systems, methods, and computer-readable storage devices for performing per-channel automatic speech recognition. An example system configured to practice the method combines a first audio signal of a first speaker in a communication session and a second audio signal from a second speaker in the communication session as a first audio channel and a second audio channel. The system can recognize speech in the first audio channel of the recording using a first model associated with the first speaker, and recognize speech in the second audio channel of the recording using a second model associated with the second speaker, wherein the first model is different from the second model. The system can generate recognized speech as an output from the communication session. The system can identify the models based on identifiers of the speakers, such as a telephone number, an IP address, a customer number, or account number.

摘要翻译： 这里公开了用于执行每通道自动语音识别的系统，方法和计算机可读存储装置。 配置为实施该方法的示例系统将通信会话中的第一扬声器的第一音频信号和来自通信会话中的第二扬声器的第二音频信号组合为第一音频通道和第二音频通道。 该系统可以使用与第一扬声器相关联的第一模型识别记录的第一音频通道中的语音，并且使用与第二扬声器相关联的第二模型识别记录的第二音频通道中的语音，其中第一模型不同 从第二个模型。 该系统可以将识别的语音产生为来自通信会话的输出。 该系统可以基于扬声器的标识符来识别模型，例如电话号码，IP地址，客户号码或帐号。

公开(公告)号：US20140032214A1

公开(公告)日：2014-01-30

申请号：US14043175

申请日：2013-10-01

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Alistair D. CONKIE ,  Ann K. Syrdal

IPC分类号： G10L15/07

CPC分类号： G10L17/14 ,  G10L15/063 ,  G10L15/07 ,  G10L15/14 ,  G10L15/187 ,  G10L15/265 ,  G10L15/30 ,  G10L2015/025

摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for recognizing speech by adapting automatic speech recognition pronunciation by acoustic model restructuring. The method identifies an acoustic model and a matching pronouncing dictionary trained on typical native speech in a target dialect. The method collects speech from a new speaker resulting in collected speech and transcribes the collected speech to generate a lattice of plausible phonemes. Then the method creates a custom speech model for representing each phoneme used in the pronouncing dictionary by a weighted sum of acoustic models for all the plausible phonemes, wherein the pronouncing dictionary does not change, but the model of the acoustic space for each phoneme in the dictionary becomes a weighted sum of the acoustic models of phonemes of the typical native speech. Finally the method includes recognizing via a processor additional speech from the target speaker using the custom speech model.

摘要翻译： 这里公开的是系统，计算机实现的方法和用于通过声学模型重构来适应自动语音识别发音来识别语音的计算机可读存储介质。 该方法识别在目标方言中典型的本地语音训练的声学模型和匹配的发音字典。 该方法从新的演讲者收集演讲，从而收集到的演讲并转录收集的演讲，以产生一个合理的音素格子。 然后，该方法创建一个自定义语音模型，用于通过用于所有似乎合理的音素的声学模型的加权和来表示在发音字典中使用的每个音素，其中发音字典不改变，而是在每个音素的声学空间的模型中 字典成为典型本地语音的音素的声学模型的加权和。 最后，该方法包括使用定制语音模型通过处理器从目标说话者识别附加语音。

公开(公告)号：US20150248884A1

公开(公告)日：2015-09-03

申请号：US14700324

申请日：2015-04-30

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Alistair D. CONKIE

IPC分类号： G10L15/07

CPC分类号： G10L15/07 ,  G10L15/04 ,  G10L15/063 ,  G10L15/083 ,  G10L15/14 ,  G10L15/22 ,  G10L15/28 ,  G10L15/32

摘要： Disclosed herein are methods, systems, and computer-readable storage media for automatic speech recognition. The method includes selecting a speaker independent model, and selecting a quantity of speaker dependent models, the quantity of speaker dependent models being based on available computing resources, the selected models including the speaker independent model and the quantity of speaker dependent models. The method also includes recognizing an utterance using each of the selected models in parallel, and selecting a dominant speech model from the selected models based on recognition accuracy using the group of selected models. The system includes a processor and modules configured to control the processor to perform the method. The computer-readable storage medium includes instructions for causing a computing device to perform the steps of the method.

摘要翻译： 这里公开了用于自动语音识别的方法，系统和计算机可读存储介质。 该方法包括选择一个说话者独立模型，并选择一个说话者依赖模型的数量，说话人依赖模型的数量是基于可用的计算资源，所选择的模型包括与说话者无关的模型和说话者依赖模型的数量。 该方法还包括使用所选择的模型中的每一个并行地识别话语，并且基于使用所选择的模型的组的识别精度从所选择的模型中选择主要语言模型。 该系统包括处理器和被配置为控制处理器执行该方法的模块。 计算机可读存储介质包括用于使计算设备执行该方法的步骤的指令。

公开(公告)号：US20150220870A1

公开(公告)日：2015-08-06

申请号：US14686929

申请日：2015-04-15

申请人： AT&T INTELLECTUAL PROPERTY I, L.P.

发明人： I. Dan MELAMED ,  Andrej LJOLJE ,  Bernard RENGER ,  Yeon-Jun KIM ,  David J. SMITH

IPC分类号： G06Q10/06 ,  G10L15/18

CPC分类号： G10L25/63 ,  G06F17/2881 ,  G06Q10/06395 ,  G10L15/04 ,  G10L15/18 ,  G10L15/1822 ,  G10L15/26 ,  G10L15/265

摘要： A method of detecting pre-determined phrases to determine compliance quality includes determining whether a precursor event has occurred based on a comparison between stored pre-determined phrases and a received communication, and determining a compliance rating based on a presence of a pre-determined phrase associated with the precursor event in the communication.

摘要翻译： 检测预定短语以确定合规质量的方法包括基于存储的预定短语和接收的通信之间的比较来确定前体事件是否已经发生，以及基于预定短语的存在来确定合规评级 与通信中的前兆事件相关联。

公开(公告)号：US20150243282A1

公开(公告)日：2015-08-27

申请号：US14698183

申请日：2015-04-28

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Alistair D. CONKIE ,  Ann K. Syrdal

IPC分类号： G10L15/187 ,  G10L15/06 ,  G10L15/14

CPC分类号： G10L17/14 ,  G10L15/063 ,  G10L15/07 ,  G10L15/14 ,  G10L15/187 ,  G10L15/265 ,  G10L15/30 ,  G10L2015/025

摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for recognizing speech by adapting automatic speech recognition pronunciation by acoustic model restructuring. The method identifies an acoustic model and a matching pronouncing dictionary trained on typical native speech in a target dialect. The method collects speech from a new speaker resulting in collected speech and transcribes the collected speech to generate a lattice of plausible phonemes. Then the method creates a custom speech model for representing each phoneme used in the pronouncing dictionary by a weighted sum of acoustic models for all the plausible phonemes, wherein the pronouncing dictionary does not change, but the model of the acoustic space for each phoneme in the dictionary becomes a weighted sum of the acoustic models of phonemes of the typical native speech. Finally the method includes recognizing via a processor additional speech from the target speaker using the custom speech model.

摘要翻译： 这里公开的是系统，计算机实现的方法和用于通过声学模型重构来适应自动语音识别发音来识别语音的计算机可读存储介质。 该方法识别在目标方言中典型的本地语音训练的声学模型和匹配的发音字典。 该方法从新的演讲者收集演讲，从而收集到的演讲并转录收集的演讲，以产生一个合理的音素格子。 然后，该方法创建一个自定义语音模型，用于通过用于所有似乎合理的音素的声学模型的加权和来表示在发音字典中使用的每个音素，其中发音字典不改变，而是在每个音素的声学空间的模型中 字典成为典型本地语音的音素的声学模型的加权和。 最后，该方法包括使用定制语音模型通过处理器从目标说话者识别附加语音。

公开(公告)号：US20150213794A1

公开(公告)日：2015-07-30

申请号：US14679508

申请日：2015-04-06

申请人： AT&T Intellectual Property I, L.P.

发明人： Andrej LJOLJE ,  Alistair D. CONKIE ,  Ann K. SYRDAL

IPC分类号： G10L15/07

CPC分类号： G10L15/07 ,  G10L15/10 ,  G10L15/265

摘要： Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for speaker recognition personalization. The method recognizes speech received from a speaker interacting with a speech interface using a set of allocated resources, the set of allocated resources including bandwidth, processor time, memory, and storage. The method records metrics associated with the recognized speech, and after recording the metrics, modifies at least one of the allocated resources in the set of allocated resources commensurate with the recorded metrics. The method recognizes additional speech from the speaker using the modified set of allocated resources. Metrics can include a speech recognition confidence score, processing speed, dialog behavior, requests for repeats, negative responses to confirmations, and task completions. The method can further store a speaker personalization profile having information for the modified set of allocated resources and recognize speech associated with the speaker based on the speaker personalization profile.

摘要翻译： 这里公开了用于说话人识别个性化的系统，计算机实现的方法和有形的计算机可读存储介质。 该方法使用一组分配的资源来识别从与语音接口交互的扬声器接收的语音，所分配的资源的集合包括带宽，处理器时间，存储器和存储。 该方法记录与识别的语音相关联的度量，并且在记录度量之后，修改与记录的度量相称的所分配资源集合中的所分配的资源中的至少一个。 该方法使用经修改的分配资源集来识别来自扬声器的附加语音。 指标可以包括语音识别置信度分数，处理速度，对话行为，重复请求，对确认的否定响应以及任务完成。 该方法还可以存储具有用于所修改的分配资源集合的信息的扬声器个性化简档，并且基于说话者个性化简档识别与说话者相关联的语音。