公开(公告)号：US06915259B2

公开(公告)日：2005-07-05

申请号：US09864838

申请日：2001-05-24

申请人： Luca Rigazio ,  Patrick Nguyen ,  David Kryze ,  Jean-Claude Junqua

发明人： Luca Rigazio ,  Patrick Nguyen ,  David Kryze ,  Jean-Claude Junqua

IPC分类号： G10L15/06 ,  G10L21/02

CPC分类号： G10L15/07 ,  G10L21/0208

摘要： Linear approximation of the background noise is applied after feature extraction and prior to speaker adaptation to allow the speaker adaptation system to adapt the speech models to the enrolling user without distortion from background noise. The linear approximation is applied in the feature domain, such as in the cepstral domain. Any adaptation technique that is commutative in the feature domain may be used.

摘要翻译： 背景噪声的线性近似在特征提取之后并且在说话者适配之前被应用，以允许扬声器适配系统将语音模型适应于登记用户，而不会从背景噪声失真。 线性近似应用于特征域，如倒谱域。 可以使用在特征域中可交换的任何适配技术。

公开(公告)号：US06907397B2

公开(公告)日：2005-06-14

申请号：US10245727

申请日：2002-09-16

申请人： David Kryze ,  Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua

发明人： David Kryze ,  Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua

IPC分类号： G10L15/00 ,  G06F17/30 ,  G10L20060101 ,  G10L11/00 ,  G10L15/04 ,  G10L15/06 ,  G10L15/18 ,  G10L15/26 ,  G10L21/00

CPC分类号： G06F17/30026 ,  G10L15/183 ,  G10L15/19 ,  G10L15/26 ,  Y10S707/99933 ,  Y10S707/99934 ,  Y10S707/99935

摘要： An embedded device for playing media files is capable of generating a play list of media files based on input speech from a user. It includes an indexer generating a plurality of speech recognition grammars. According to one aspect of the invention, the indexer generates speech recognition grammars based on contents of a media file header of the media file. According to another aspect of the invention, the indexer generates speech recognition grammars based on categories in a file path for retrieving the media file to a user location. When a speech recognizer receives an input speech from a user while in a selection mode, a media file selector compares the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

摘要翻译： 用于播放媒体文件的嵌入式设备能够基于来自用户的输入语音来生成媒体文件的播放列表。 它包括产生多个语音识别语法的索引器。 根据本发明的一个方面，索引器基于媒体文件的媒体文件头的内容生成语音识别语法。 根据本发明的另一方面，索引器基于用于将媒体文件检索到用户位置的文件路径中的类别来生成语音识别语法。 当语音识别器在选择模式下从用户接收到输入语音时，媒体文件选择器将选择模式下接收到的输入语音与多个语音识别语法进行比较，从而选择媒体文件。

公开(公告)号：US06901364B2

公开(公告)日：2005-05-31

申请号：US09951093

申请日：2001-09-13

申请人： Patrick Nguyen ,  Luca Rigazio ,  Jean-Claude Junqua

发明人： Patrick Nguyen ,  Luca Rigazio ,  Jean-Claude Junqua

IPC分类号： G10L15/18 ,  G10L15/28 ,  G10L15/26 ,  G06F17/20 ,  G10L21/00

CPC分类号： G10L15/1815 ,  G10L15/30

摘要： An e-mail message process is provided for use with a personal digital assistant which allows for the use of input speech messaging which is converted to text using a focused language model which is downloaded by a cellular phone connection to an Internet server which provides the focused language model based upon a topic for the intended e-mail message. The text that is generated from the input speech method can be summarized by the e-mail message processor and can be edited by the user. The generated e-mail message can then be transmitted again via cellular connection to an Internet e-mail server for transmitting the e-mail message to a recipient.

摘要翻译： 提供电子邮件消息处理以与个人数字助理一起使用，该个人数字助理允许使用输入语音消息传送，其使用由通过蜂窝电话连接下载的聚焦语言模型转换为文本，该互联网服务器提供聚焦 基于预期电子邮件的主题的语言模型。 从输入语音方法生成的文本可以由电子邮件消息处理器来总结，并且可以由用户编辑。 然后可以通过蜂窝连接再次将生成的电子邮件消息发送到Internet电子邮件服务器，以将电子邮件消息发送给接收者。

公开(公告)号：US20050075881A1

公开(公告)日：2005-04-07

申请号：US10677174

申请日：2003-10-02

申请人： Luca Rigazio ,  Robert Boman ,  Patrick Nguyen ,  Jean-Claude Junqua

发明人： Luca Rigazio ,  Robert Boman ,  Patrick Nguyen ,  Jean-Claude Junqua

IPC分类号： G10L15/26 ,  G10L21/00

CPC分类号： G06F17/30796 ,  G10L15/26

摘要： A media capture device has an audio input receptive of user speech relating to a media capture activity in close temporal relation to the media capture activity. A plurality of focused speech recognition lexica respectively relating to media capture activities are stored on the device, and a speech recognizer recognizes the user speech based on a selected one of the focused speech recognition lexica. A media tagger tags captured media with generated speech recognition text, and a media annotator annotates the captured media with a sample of the user speech that is suitable for input to a speech recognizer. Tagging and annotating are based on close temporal relation between receipt of the user speech and capture of the captured media. Annotations may be converted to tags during post processing, employed to edit a lexicon using letter-to-sound rules and spelled word input, or matched directly to speech to retrieve captured media.

摘要翻译： 媒体捕获设备具有接收与媒体捕获活动紧密相关的媒体捕获活动的用户语音的音频输入。 分别与媒体捕获活动相关的多个聚焦语音识别词典被存储在设备上，并且语音识别器基于所选择的一个焦点语音识别词典识别用户语音。 媒体标签器使用生成的语音识别文本来标记捕获的媒体，并且媒体注释器用适合于输入到语音识别器的用户语音的样本来注释所捕获的媒体。 标记和注释是基于用户语音的接收和捕获的媒体的捕获之间的紧密的时间关系。 在后期处理中，注释可以转换为标签，用于使用字母对声音规则和拼写单词输入来编辑词典，或直接与语音匹配以检索所捕获的媒体。

公开(公告)号：US07089182B2

公开(公告)日：2006-08-08

申请号：US10099305

申请日：2002-03-15

申请人： Younes Souilmi ,  Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua

发明人： Younes Souilmi ,  Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua

IPC分类号： G10L15/20

CPC分类号： G10L15/20 ,  G10L15/02 ,  G10L15/063 ,  G10L21/0216

摘要： A method for performing noise adaptation of a target speech signal input to a speech recognition system, where the target speech signal contains both additive and convolutional noises. The method includes estimating an additive noise bias and a convolutional noise bias; in the target speech signal; and jointly compensating the target speech signal for the additive and convolutional noise biases in a feature domain.

公开(公告)号：US07324943B2

公开(公告)日：2008-01-29

申请号：US10677174

申请日：2003-10-02

申请人： Luca Rigazio ,  Robert Boman ,  Patrick Nguyen ,  Jean-Claude Junqua

发明人： Luca Rigazio ,  Robert Boman ,  Patrick Nguyen ,  Jean-Claude Junqua

IPC分类号： G10L21/00 ,  H04N5/76

CPC分类号： G06F17/30796 ,  G10L15/26

摘要： A media capture device has an audio input receptive of user speech relating to a media capture activity in close temporal relation to the media capture activity. A plurality of focused speech recognition lexica respectively relating to media capture activities are stored on the device, and a speech recognizer recognizes the user speech based on a selected one of the focused speech recognition lexica. A media tagger tags captured media with generated speech recognition text, and a media annotator annotates the captured media with a sample of the user speech that is suitable for input to a speech recognizer. Tagging and annotating are based on close temporal relation between receipt of the user speech and capture of the captured media. Annotations may be converted to tags during post processing, employed to edit a lexicon using letter-to-sound rules and spelled word input, or matched directly to speech to retrieve captured media.

摘要翻译： 媒体捕获设备具有接收与媒体捕获活动紧密相关的媒体捕获活动的用户语音的音频输入。 分别与媒体捕获活动相关的多个聚焦语音识别词典被存储在设备上，并且语音识别器基于所选择的一个焦点语音识别词典识别用户语音。 媒体标签器使用生成的语音识别文本来标记捕获的媒体，并且媒体注释器用适合于输入到语音识别器的用户语音的样本来注释所捕获的媒体。 标记和注释是基于用户语音的接收和捕获的媒体的捕获之间的紧密的时间关系。 在后期处理中，注释可以转换为标签，用于使用字母对声音规则和拼写单词输入来编辑词典，或直接与语音匹配以检索所捕获的媒体。

公开(公告)号：US20050010411A1

公开(公告)日：2005-01-13

申请号：US10616006

申请日：2003-07-09

申请人： Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua ,  Robert Boman

发明人： Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua ,  Robert Boman

IPC分类号： G10L15/26 ,  G10L17/00 ,  G10L15/00

CPC分类号： G10L15/26 ,  G10L17/00

摘要： A speech data mining system for use in generating a rich transcription having utility in call center management includes a speech differentiation module differentiating between speech of interacting speakers, and a speech recognition module improving automatic recognition of speech of one speaker based on interaction with another speaker employed as a reference speaker. A transcript generation module generates a rich transcript based on recognized speech of the speakers. Focused, interactive language models improve recognition of a customer on a low quality channel using context extracted from speech of a call center operator on a high quality channel with a speech model adapted to the operator. Mined speech data includes number of interaction turns, customer frustration phrases, operator polity, interruptions, and/or contexts extracted from speech recognition results, such as topics, complaints, solutions, and resolutions. Mined speech data is useful in call center and/or product or service quality management.

摘要翻译： 用于产生在呼叫中心管理中具有效用的丰富录音的语音数据挖掘系统包括区分交互式扬声器的语音的语音区分模块和改善一个扬声器的语音的自动识别的语音识别模块， 作为参考发言人。 转录本生成模块基于扬声器的识别语音生成丰富的录音。 专注的交互式语言模型通过使用适合于操作员的语音模型，在高质量频道上从呼叫中心运营商的语音提取的上下文，改善对低质量信道上客户的识别。 挖掘的语音数据包括从诸如主题，投诉，解决方案和分辨率的语音识别结果中提取的交互轮廓数量，客户沮丧短语，运营商政治，中断和/或上下文。 挖掘的语音数据在呼叫中心和/或产品或服务质量管理中是有用的。

公开(公告)号：US06687672B2

公开(公告)日：2004-02-03

申请号：US10099428

申请日：2002-03-15

申请人： Younes Souilmi ,  Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua

发明人： Younes Souilmi ,  Luca Rigazio ,  Patrick Nguyen ,  Jean-Claude Junqua

IPC分类号： G10L1508

CPC分类号： G10L21/0208

摘要： Methods and apparatus for blind channel estimation of a speech signal corrupted by a communication channel are provided. One method includes converting a noisy speech signal into either a cepstral representation or a log-spectral representation; estimating a correlation of the representation of the noisy speech signal; determining an average of the noisy speech signal; constructing and solving, subject to a minimization constraint, a system of linear equations utilizing a correlation structure of a clean speech training signal, the correlation of the representation of the noisy speech signal, and the average of the noisy speech signal; and selecting a sign of the solution of the system of linear equations to estimate an average clean speech signal in a processing window.

摘要翻译： 提供了由通信信道损坏的语音信号的盲信道估计的方法和装置。 一种方法包括将噪声语音信号转换成倒谱表示或对数谱表示; 估计噪声语音信号的表示的相关性; 确定噪声语音信号的平均值; 利用最小化约束，构建和求解利用清晰语音训练信号的相关结构，噪声语音信号的表示与噪声语音信号的平均值的相关性的线性方程组; 以及选择线性方程式的解的符号来估计处理窗口中的平均清洁语音信号。

公开(公告)号：US06895376B2

公开(公告)日：2005-05-17

申请号：US09849174

申请日：2001-05-04

申请人： Florent Perronnin ,  Roland Kuhn ,  Patrick Nguyen ,  Jean-Claude Junqua

发明人： Florent Perronnin ,  Roland Kuhn ,  Patrick Nguyen ,  Jean-Claude Junqua

IPC分类号： G10L15/06 ,  G10L17/00

CPC分类号： G10L15/07 ,  G10L17/02

摘要： A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. Re-estimation processes are performed to more strongly separate speaker-dependent and speaker-independent components of the speech model. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation.

摘要翻译： 在训练期间使用减小的维度本征语音分析技术来开发用于异音素的上下文相关的声学模型。 执行重新估计过程以更强烈地分离语音模型的与扬声器相关的和与扬声器无关的组件。 特定语音技术在运行时也用于新演讲者的演讲。 该技术可以消除单个扬声器的特性，从而产生更普遍适用和强大的异音模型。 在一个实施例中，本征语音技术用于识别每个说话者的质心，然后可以将其“减去”识别方程。

公开(公告)号：US06263309B1

公开(公告)日：2001-07-17

申请号：US09070054

申请日：1998-04-30

申请人： Patrick Nguyen ,  Roland Kuhn ,  Jean-Claude Junqua

发明人： Patrick Nguyen ,  Roland Kuhn ,  Jean-Claude Junqua

IPC分类号： G10L1508

CPC分类号： G10L15/07

摘要： A set of speaker dependent models is trained upon a comparatively large number of training speakers, one model per speaker, and model parameters are extracted in a predefined order to construct a set of supervectors, one per speaker. Principle component analysis is then performed on the set of supervectors to generate a set of eigenvectors that define an eigenvoice space. If desired, the number of vectors may be reduced to achieve data compression. Thereafter, a new speaker provides adaptation data from which a supervector is constructed by constraining this supervector to be in the eigenvoice space based on a maximum likelihood estimation. The resulting coefficients in the eigenspace of this new speaker may then be used to construct a new set of model parameters from which an adapted model is constructed for that speaker. Environmental adaptation may be performed by including environmental variations in the training data.

摘要翻译： 一组扬声器依赖模型训练在相对较多数量的训练扬声器上，每个扬声器一个模型和模型参数以预定义的顺序提取，以构建一组超级矢量，每个扬声器一个。 然后在一组超级矢量上执行原理分量分析，以生成一组定义本征语音空间的特征向量。 如果需要，可以减少向量的数量以实现数据压缩。 此后，新的说话者提供了通过基于最大似然估计将该超向量限制在本征语音空间中来构建超向量的适配数据。 然后，可以使用这个新的说话者的本征空间中得到的系数来构建一组新的模型参数，从该模型参数构建适合于该说话者的适应模型。 可以通过在训练数据中包括环境变化来执行环境适应。