-
1.发明授权Method for learning linguistically valid word pronunciations from acoustic data 有权从声学数据学习语言有效的单词发音的方法公开(公告)号：US07280963B1
公开(公告)日：2007-10-09
申请号：US10660868
申请日：2003-09-12
CPC分类号： G10L15/187 , G10L15/06
摘要： A computerized method is provided for generating pronunciations for words and storing the pronunciations in a pronunciation dictionary. The method includes graphing sets of initial pronunciations; thereafter in an ASR subsystem determining a highest-scoring set of initial pronunciations; generating sets of alternate pronunciations, wherein each set of alternate pronunciations includes the highest-scoring set of initial pronunciations with a lowest-probability phone of the highest-scoring initial pronunciation substituted with a unique-substitute phone; graphing the sets of alternate pronunciations; determining in the ASR subsystem a highest-scoring set of alternate pronunciations; and adding to a pronunciation dictionary the highest-scoring set of alternate pronunciations.
摘要翻译： 提供了一种计算机化方法，用于产生词的发音并将发音存储在发音词典中。 该方法包括绘制初始发音集合; 之后在ASR子系统中确定最高评分的初始发音集; 生成替代发音的集合，其中每组交替发音包括用唯一替代电话替代最高得分的初始发音的最低概率电话的最高得分的初始发音集; 绘制交替发音的集合; 在ASR子系统中确定最高分的一组交替发音; 并添加一个发音词典最高评分的交替发音。
-
2.发明授权Method and system for learning linguistically valid word pronunciations from acoustic data 有权从声学数据学习语言有效的单词发音的方法和系统公开(公告)号：US07266495B1
公开(公告)日：2007-09-04
申请号：US10661106
申请日：2003-09-12
CPC分类号： G10L15/06 , G10L15/187
摘要： A computerized pronunciation system is provided for generating pronunciations for words and storing the pronunciations in a pronunciation dictionary. The system includes a word list including at least one word; transcribed acoustic data including at least one waveform for the word and transcribed text associated with the waveform; a pronunciation-learning module configured to accept as input the word list and the transcribed acoustic data, the pronunciation-learning module including: sets of initial pronunciations of the word, a scoring module configured score pronunciations and to generate phone probabilities, and a set of alternate pronunciations of the word, wherein the set of alternate pronunciations include a highest-scoring set of initial pronunciations with a highest-scoring substitute phone substituted for a lowest-probability phone; and a pronunciation dictionary configured to receive the highest-scoring set of initial pronunciations and the set of alternate pronunciations.
摘要翻译： 提供了一种计算机化的发音系统，用于产生词的发音并将发音存储在发音词典中。 该系统包括包括至少一个单词的单词列表; 转录声学数据，包括用于该词的至少一个波形和与波形相关联的转录文本; 发音学习模块，被配置为接受单词列表和转录声学数据的输入，所述发音学习模块包括：该单词的初始发音集，评分模块配置得分发音并产生电话概率，以及一组 该单词的替代发音，其中该组交替发音包括最高得分的初始发音集合，其中替代最低概率电话的最高评分替代电话; 和发音词典，其配置为接收最高分的初始发音和一组交替发音。
-
公开(公告)号：US06804640B1
公开(公告)日：2004-10-12
申请号：US09515252
申请日：2000-02-29
IPC分类号： G10L1520
CPC分类号： G10L21/0208 , G10L15/20 , G10L19/0204 , G10L21/0216 , H04L1/20
摘要： A method and apparatus for generating a noise-reduced feature vector representing human speech are provided. Speech data representing an input speech waveform are first input and filtered. Spectral energies of the filtered speech data are determined, and a noise reduction process is then performed. In the noise reduction process, a spectral magnitude is computed for a frequency index of multiple frequency indexes. A noise magnitude estimate is then determined for the frequency index by updating a histogram of spectral magnitude, and then determining the noise magnitude estimate as a predetermined percentile of the histogram. A signal-to-noise ratio is then determined for the frequency index. A scale factor is computed for the frequency index, as a function of the signal-to-noise ratio and the noise magnitude estimate. The noise magnitude estimate is then scaled by the scale factor. The scaled noise magnitude estimate is subtracted from the spectral magnitudes of the filtered speech data, to produce cleaned speech data, based on which a feature vector is generated.
摘要翻译： 提供了一种用于生成表示人类语音的降噪特征向量的方法和装置。 首先输入和过滤表示输入语音波形的语音数据。 确定滤波后的语音数据的频谱能量，然后进行降噪处理。 在降噪过程中，针对多个频率指标的频率指数计算频谱幅度。 然后通过更新频谱幅度的直方图来确定频率索引的噪声幅度估计，然后将噪声幅度估计确定为直方图的预定百分位数。 然后确定频率指数的信噪比。 作为信噪比和噪声幅度估计的函数，针对频率指数计算比例因子。 然后通过比例因子缩放噪声幅度估计。 从经滤波的语音数据的频谱幅度中减去缩放的噪声幅度估计，以产生清除的语音数据，基于此产生特征向量。
-
公开(公告)号：US20220368343A1
公开(公告)日：2022-11-17
申请号：US17620448
申请日：2019-09-09
申请人： Giovanni MOTTA , Francoise BEAUFAYS , Petr ZADRAZIL , Google LLC
摘要： Systems and methods for compression of data that exhibits mixed compressibility, such as floating-point data, are provided. As one example, aspects of the present disclosure can be used to compress floating-point data that represents the values of parameters of a machine-learned model. Therefore, aspects of the present disclosure can be used to compress machine-learned models (e.g., for reducing storage requirements associated with the model, reducing the bandwidth expended to transmit the model, etc.).
-
公开(公告)号：US07890326B2
公开(公告)日：2011-02-15
申请号：US11549486
申请日：2006-10-13
IPC分类号： G10L21/00
CPC分类号： G10L2015/228
摘要： A method of operating a voice-enabled business directory search system includes selecting a subset of speech recognition language models from a larger set of speech recognition language models based on a type of business provided by a user, identifying weight values for the selected language models, and recognizing an identifier of a specific business in a speech input from the user based on the selected language models and the weight values.
摘要翻译： 操作启用语音的商业目录搜索系统的方法包括：基于由用户提供的业务类型，识别所选语言模型的权重值，从较大语言识别语言模型集中选择语音识别语言模型的子集， 并且基于所选择的语言模型和权重值，识别来自用户的语音输入中的特定业务的标识符。
-
公开(公告)号：US20080091435A1
公开(公告)日：2008-04-17
申请号：US11549486
申请日：2006-10-13
IPC分类号： G10L11/00
CPC分类号： G10L2015/228
摘要： A method of operating a voice-enabled business directory search system includes selecting a subset of speech recognition language models from a larger set of speech recognition language models based on a type of business provided by a user, identifying weight values for the selected language models, and recognizing an identifier of a specific business in a speech input from the user based on the selected language models and the weight values.
摘要翻译： 操作启用语音的商业目录搜索系统的方法包括：基于由用户提供的业务类型，识别所选语言模型的权重值，从较大语言识别语言模型集中选择语音识别语言模型的子集， 并且基于所选择的语言模型和权重值，识别来自用户的语音输入中的特定业务的标识符。
-
7.发明申请公开(公告)号：US20070239531A1
公开(公告)日：2007-10-11
申请号：US11394143
申请日：2006-03-30
IPC分类号： G06Q30/00
CPC分类号： G06Q30/00 , G06Q30/0257 , G06Q30/0273
摘要： A request for listing information is received, and if the request is determined to be for an unspecific listing, a number of ads are served prior to delivery of the requested listings. If the request is determined to not be for an unspecific business, a lesser number (or zero) ads are served prior to delivery of the requested listings. The determination of the request as being unspecific can be made by comparing the request to a list of unspecific requests, determining if the request exactly matches a listing, or by other means. Ads served result in the advertiser being assessed a per-impression charge.
摘要翻译： 接收到列表信息的请求，并且如果确定该请求用于非特定列表，则在递送所请求的列表之前提供多个广告。 如果请求被确定为不是针对非特定业务，则在提交所请求的列表之前，会提供较少数量（或零）的广告。 将请求确定为非特定的可以通过将请求与非特定请求列表进行比较，确定请求是否与列表完全匹配，或通过其他方式来进行。 广告投放导致广告客户被评估为每次展示费用。
-
公开(公告)号：US08364481B2
公开(公告)日：2013-01-29
申请号：US12166822
申请日：2008-07-02
申请人： Brian Strope , Francoise Beaufays , Olivier Siohan
发明人： Brian Strope , Francoise Beaufays , Olivier Siohan
IPC分类号： G10L15/00
摘要： The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal and initiating speech recognition tasks by a plurality of speech recognition systems (SRS's). Each SRS is configured to generate a recognition result specifying possible speech included in the audio signal and a confidence value indicating a confidence in a correctness of the speech result. The method also includes completing a portion of the speech recognition tasks including generating one or more recognition results and one or more confidence values for the one or more recognition results, determining whether the one or more confidence values meets a confidence threshold, aborting a remaining portion of the speech recognition tasks for SRS's that have not completed generating a recognition result, and outputting a final recognition result based on at least one of the generated one or more speech results.
摘要翻译： 除了别的以外，本说明书的主题可以体现在包括通过多个语音识别系统（SRS）接收音频信号和发起语音识别任务的方法。 每个SRS被配置为产生指定包括在音频信号中的可能语音的识别结果，以及指示对语音结果的正确性置信度的置信度值。 该方法还包括完成语音识别任务的一部分，包括生成一个或多个识别结果和一个或多个识别结果的一个或多个置信度值，确定一个或多个置信度值是否满足置信阈值，中止其余部分 的尚未完成生成识别结果的SRS的语音识别任务，并且基于所生成的一个或多个语音结果中的至少一个来输出最终识别结果。
-
公开(公告)号：US20120020254A1
公开(公告)日：2012-01-26
申请号：US13249623
申请日：2011-09-30
申请人： Brian Strope , Francoise Beaufays , Hy Murveit
发明人： Brian Strope , Francoise Beaufays , Hy Murveit
CPC分类号： H04L61/106 , H04L12/66 , H04L51/28 , H04L51/32 , H04L51/36 , H04M1/7255 , H04M3/42102 , H04W4/16 , H04W8/183
摘要： In one implementation a computer-implemented method includes generating a group of telephone contacts for a first user, wherein the generating includes identifying a second user as a contact of the first user based upon a determination that the second user has at least a threshold email-based association with the first user; and adding the identified second user to the group of telephone contacts for the first user. The method further includes receiving a first request to connect a first telephone device associated with the first user to a second telephone device associated with the second user. The method also includes identifying a contact identifier of the second telephone device using the generated group of telephone contacts for the first user, and initiating a connection between the first telephone device and the second telephone device using the identified contact identifier.
摘要翻译： 在一个实现中，计算机实现的方法包括为第一用户生成一组电话联系人，其中生成包括基于第二用户至少具有阈值电子邮件地址的确定来将第二用户识别为第一用户的联系人， 与第一个用户的关联; 以及将所识别的第二用户添加到第一用户的电话联系人组。 该方法还包括接收将与第一用户相关联的第一电话设备连接到与第二用户相关联的第二电话设备的第一请求。 该方法还包括使用生成的第一用户的电话联系人识别第二电话设备的联系人标识符，以及使用所识别的联系人标识符来启动第一电话设备和第二电话设备之间的连接。
-
公开(公告)号：US07840407B2
公开(公告)日：2010-11-23
申请号：US11549484
申请日：2006-10-13
IPC分类号： G06F17/21
CPC分类号： G10L15/22 , G06F17/30241 , G06F17/30864 , G06F17/30867 , G06F17/3087 , G06Q30/02 , G10L15/18 , G10L15/197 , G10L15/26 , G10L15/30 , G10L2015/223 , G10L2015/228
摘要： A method of operating a voice-enabled business directory search system includes receiving category-business pairs, each category-business pair including a business category and a specific business, and establishing a data structure having nodes based on the category-business pairs. Each node of the data structure is associated with one or more business categories and a speech recognition language model for recognizing specific businesses associated with the one or more businesses categories.
摘要翻译： 操作启用语音的业务目录搜索系统的方法包括接收类别业务对，每个类别业务对包括业务类别和特定业务，以及基于类别业务对建立具有节点的数据结构。 数据结构的每个节点与一个或多个业务类别和用于识别与一个或多个业务类别相关联的特定业务的语音识别语言模型相关联。
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.023 秒)
