公开(公告)号：US20110137653A1

公开(公告)日：2011-06-09

申请号：US12631111

申请日：2009-12-04

申请人： Andrej LJOLJE ,  Mazin Gilbert

发明人： Andrej LJOLJE ,  Mazin Gilbert

IPC分类号： G10L15/00

CPC分类号： G10L15/183 ,  G10L2015/227 ,  G10L2015/228

摘要： Disclosed herein are systems, methods, and computer-readable storage media for performing speech recognition based on a masked language model. A system configured to practice the method receives a masked language model including a plurality of words, wherein a bit mask identifies whether each of the plurality of words is allowed or disallowed with regard to an adaptation subset, receives input speech, generates a speech recognition lattice based on the received input speech using the masked language model, removes from the generated lattice words identified as disallowed by the bit mask for the adaptation subset, and recognizes the received speech based on the lattice. Alternatively during the generation step, the system can only add words indicated as allowed by the bit mask. The bit mask can be separate from or incorporated as part of the masked language model. The system can dynamically update the adaptation subset and bit mask.

摘要翻译： 本文公开了用于基于掩蔽语言模型执行语音识别的系统，方法和计算机可读存储介质。 被配置为实施该方法的系统接收包括多个单词的掩蔽语言模型，其中位掩码识别关于自适应子集是否允许或不允许多个单词中的每一个，接收输入语音，生成语音识别格 基于使用掩蔽语言模型的接收到的输入语音，从由适配子集的位掩码识别为不允许的生成的格子字中移除，并且基于格子识别接收的语音。 或者在生成步骤期间，系统只能添加由位掩码允许的指示的字。 位掩码可以与掩蔽语言模型的一部分分开或并入。 系统可以动态地更新自适应子集和位掩码。

公开(公告)号：US20120290298A1

公开(公告)日：2012-11-15

申请号：US13103665

申请日：2011-05-09

申请人： Andrej LJOLJE ,  Diamantino Antonio Caseiro ,  Mazin Gilbert ,  Vincent Goffin ,  Taniya Mishra

发明人： Andrej LJOLJE ,  Diamantino Antonio Caseiro ,  Mazin Gilbert ,  Vincent Goffin ,  Taniya Mishra

IPC分类号： G10L15/26

CPC分类号： G10L15/197 ,  G10L15/063 ,  G10L15/22

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.

摘要翻译： 这里公开了用于将显着权重分配给ASR模型的单词的系统，方法和非暂时计算机可读存储介质。 分配给ASR模型中的单词的显着性值基于以前的成绩单的人类感知判断。 这些显着性值被用作权重以修改ASR模型，使得将口头文档转换成抄本的加权ASR模型的结果为用户提供更准确和有用的转录。

公开(公告)号：US20150348540A1

公开(公告)日：2015-12-03

申请号：US14287866

申请日：2014-05-27

申请人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Mazin GILBERT GILBERT ,  Vincent GOFFIN ,  Taniya Mishra

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

IPC分类号： 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.

摘要翻译： 这里公开了用于将显着权重分配给ASR模型的单词的系统，方法和非暂时计算机可读存储介质。 分配给ASR模型中的单词的显着性值基于以前的成绩单的人类感知判断。 这些显着性值被用作权重以修改ASR模型，使得将口头文档转换成抄本的加权ASR模型的结果为用户提供更准确和有用的转录。

公开(公告)号：US20110137648A1

公开(公告)日：2011-06-09

申请号：US12631131

申请日：2009-12-04

申请人： Andrej LJOLJE ,  Mazin GILBERT

发明人： Andrej LJOLJE ,  Mazin GILBERT

IPC分类号： G10L15/00

CPC分类号： G10L15/00 ,  G10L15/285 ,  G10L15/32

摘要： Disclosed herein are systems, methods, and computer-readable storage media for improving automatic speech recognition performance. A system practicing the method identifies idle speech recognition resources and establishes a supplemental speech recognizer on the idle resources based on overall speech recognition demand. The supplemental speech recognizer can differ from a main speech recognizer, and, along with the main speech recognizer, can be associated with a particular speaker. The system performs speech recognition on speech received from the particular speaker in parallel with the main speech recognizer and the supplemental speech recognizer and combines results from the main and supplemental speech recognizer. The system recognizes the received speech based on the combined results. The system can use beam adjustment in place of or in combination with a supplemental speech recognizer. A scheduling algorithm can tailor a particular combination of speech recognition resources and release the supplemental speech recognizer based on increased demand.

摘要翻译： 本文公开了用于改善自动语音识别性能的系统，方法和计算机可读存储介质。 实施该方法的系统识别空闲语音识别资源，并且基于总体语音识别需求在空闲资源上建立补充语音识别器。 补充语音识别器可以与主语音识别器不同，并且与主语音识别器一起可以与特定扬声器相关联。 该系统与主语音识别器和辅助语音识别器并行地执行从特定扬声器接收的语音的语音识别，并且组合来自主语音识别器和补充语音识别器的结果。 系统基于组合的结果识别接收到的语音。 该系统可以使用波束调整来代替或与补充语音识别器组合。 调度算法可以定制语音识别资源的特定组合，并且基于增加的需求来释放补充语音识别器。

公开(公告)号：US20110137650A1

公开(公告)日：2011-06-09

申请号：US12633334

申请日：2009-12-08

申请人： Andrej LJOLJE

发明人： Andrej LJOLJE

IPC分类号： G10L15/14 ,  G10L15/06

CPC分类号： G10L15/144 ,  G10L15/063

摘要： Disclosed herein are systems, methods, and computer-readable storage media for training adaptation-specific acoustic models. A system practicing the method receives speech and generates a full size model and a reduced size model, the reduced size model starting with a single distribution for each speech sound in the received speech. The system finds speech segment boundaries in the speech using the full size model and adapts features of the speech data using the reduced size model based on the speech segment boundaries and an overall centroid for each speech sound. The system then recognizes speech using the adapted features of the speech. The model can be a Hidden Markov Model (HMM). The reduced size model can also be of a reduced complexity, such as having fewer mixture components than a model of full complexity. Adapting features of speech can include moving the features closer to an overall feature distribution center.

摘要翻译： 本文公开了用于训练适应特定声学模型的系统，方法和计算机可读存储介质。 实施该方法的系统接收语音并生成全尺寸模型和缩小尺寸模型，缩小尺寸模型从接收到的语音中的每个语音的单个分布开始。 该系统使用全尺寸模型在语音中找到语音段边界，并且使用基于语音段边界的缩小尺寸模型和每个语音的整体质心来适应语音数据的特征。 该系统然后使用该语音的适应特征识别语音。 该模型可以是隐马尔可夫模型（HMM）。 缩小的尺寸模型也可以是降低的复杂性，例如具有比完全复杂性的模型更少的混合分量。 适应语音功能可以包括将功能移动到更接近整体功能分配中心。

公开(公告)号：US20110119059A1

公开(公告)日：2011-05-19

申请号：US12618371

申请日：2009-11-13

申请人： Andrej LJOLJE ,  Bernard S. RENGER ,  Steven Neil TISCHER

发明人： Andrej LJOLJE ,  Bernard S. RENGER ,  Steven Neil TISCHER

IPC分类号： G10L15/06 ,  G10L15/00 ,  G10L11/00

CPC分类号： G10L15/075 ,  G10L15/063 ,  G10L15/065 ,  G10L15/07 ,  G10L15/08

摘要： Disclosed herein are systems, methods, and computer-readable storage media for selecting a speech recognition model in a standardized speech recognition infrastructure. The system receives speech from a user, and if a user-specific supervised speech model associated with the user is available, retrieves the supervised speech model. If the user-specific supervised speech model is unavailable and if an unsupervised speech model is available, the system retrieves the unsupervised speech model. If the user-specific supervised speech model and the unsupervised speech model are unavailable, the system retrieves a generic speech model associated with the user. Next the system recognizes the received speech from the user with the retrieved model. In one embodiment, the system trains a speech recognition model in a standardized speech recognition infrastructure. In another embodiment, the system handshakes with a remote application in a standardized speech recognition infrastructure.

摘要翻译： 这里公开了用于在标准化语音识别基础设施中选择语音识别模型的系统，方法和计算机可读存储介质。 系统从用户接收语音，并且如果与用户相关联的用户特定的监督语音模型可用，则检索监督的语音模型。 如果用户特定的监督语音模型不可用，并且如果无人监督的语音模型可用，则系统检索无监督语音模型。 如果用户特定的监督语音模型和无监督语音模型不可用，则系统检索与用户相关联的通用语音模型。 接下来，系统使用所检索的模型识别来自用户的接收到的语音。 在一个实施例中，系统在标准化语音识别基础设施中训练语音识别模型。 在另一个实施例中，系统与标准语音识别基础设施中的远程应用握手。

公开(公告)号：US20110066433A1

公开(公告)日：2011-03-17

申请号：US12561005

申请日：2009-09-16

申请人： Andrej LJOLJE ,  Diamantino Antonio CASEIRO ,  Alistair D. CONKIE

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

IPC分类号： G10L15/00

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：US20110077942A1

公开(公告)日：2011-03-31

申请号：US12570757

申请日：2009-09-30

申请人： Andrej LJOLJE ,  Diamantino Antonio Caseiro

发明人： Andrej LJOLJE ,  Diamantino Antonio Caseiro

IPC分类号： G10L15/06

CPC分类号： G10L15/1815 ,  G10L15/063 ,  G10L15/065 ,  G10L15/183 ,  G10L15/22

摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for handling expected repeat speech queries or other inputs. The method causes a computing device to detect a misrecognized speech query from a user, determine a tendency of the user to repeat speech queries based on previous user interactions, and adapt a speech recognition model based on the determined tendency before an expected repeat speech query. The method can further include recognizing the expected repeat speech query from the user based on the adapted speech recognition model. Adapting the speech recognition model can include modifying an acoustic model, a language model, and/or a semantic model. Adapting the speech recognition model can also include preparing a personalized search speech recognition model for the expected repeat query based on usage history and entries in a recognition lattice. The method can include retaining unmodified speech recognition models with adapted speech recognition models.

摘要翻译： 本文公开了用于处理预期重复语音查询或其他输入的系统，计算机实现的方法和计算机可读存储介质。 该方法使得计算设备检测来自用户的误识别语音查询，确定用户基于先前用户交互重复语音查询的趋势，以及基于在预期重复语音查询之前确定的趋势来调整语音识别模型。 该方法还可以包括基于适应的语音识别模型识别来自用户的预期重复语音查询。 适应语音识别模型可以包括修改声学模型，语言模型和/或语义模型。 适应语音识别模型还可以包括基于使用历史和识别格中的条目为预期重复查询准备个性化搜索语音识别模型。 该方法可以包括使用适应的语音识别模型保留未修改的语音识别模型。

公开(公告)号：US20100161315A1

公开(公告)日：2010-06-24

申请号：US12343981

申请日：2008-12-24

申请人： I. Dan MELAMED ,  Yeon-Jun KIM ,  Bernard S. RENGER ,  Andrej LJOLJE ,  David J. SMITH

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

IPC分类号： G06F17/27 ,  G10L15/26

CPC分类号： G06F17/2715 ,  G10L15/26 ,  G10L17/00

摘要： A method of correlating received communication data with operational communication characteristics is provided. The method includes receiving audible input from a source in a communication over a communications network, recording the received audible input, and transcribing the recorded audible input into a transcript. The method further includes outputting the transcript, specifying features of the transcript to be analyzed, specifying and recording operational communication characteristics particular to the communication, analyzing the transcript for the specified features to identify patterns associated with the audible input, computing statistical correlations of the identified patterns with the operational communication characteristics, and outputting results of the computed statistical correlations on a user interface.

摘要翻译： 提供了一种使接收到的通信数据与操作通信特性相关的方法。 该方法包括通过通信网络在通信中接收来自源的可听输入，记录所接收的可听输入，以及将记录的可听输入转录成抄本。 该方法还包括输出抄本，指定要分析的抄本的特征，指定和记录特定于通信的操作通信特征，分析指定特征的抄本以识别与可听见输入相关联的模式，计算所识别的 具有操作通信特性的模式，并且在用户界面上输出所计算的统计相关性的结果。

公开(公告)号：US20100332286A1

公开(公告)日：2010-12-30

申请号：US12490662

申请日：2009-06-24

申请人： I. Dan MELAMED ,  Yeon-Jun KIM ,  Andrej LJOLJE ,  Bernard S. RENGER ,  David J. SMITH

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

IPC分类号： G06Q10/00 ,  G06N7/02

CPC分类号： G06Q30/0203 ,  G06Q10/10 ,  G06Q30/0245

摘要： Predicting a score related to a communication sent by a sender over a communications network to a first agent servicing the communication includes obtaining a regression result for an objective function by encoding features extracted from the communication. The encoded features are applied to a regression model for the objective function. The regression result is output to a network component in the communications network. The regression model is determined prior to or concurrently with receiving the communication from the sender.

摘要翻译： 预测与发送方通过通信网络发送的通信相关的评分与服务于通信的第一代理包括通过对从通信提取的特征进行编码来获得目标函数的回归结果。 编码的特征被应用于目标函数的回归模型。 回归结果输出到通信网络中的网络组件。 在从发送者接收通信之前或同时确定回归模型。