-
公开(公告)号：US20110224982A1
公开(公告)日：2011-09-15
申请号：US12722556
申请日：2010-03-12
IPC分类号： G10L15/02
CPC分类号： G10L15/08 , G10L2015/025
摘要： Described is a technology in which information retrieval (IR) techniques are used in a speech recognition (ASR) system. Acoustic units (e.g., phones, syllables, multi-phone units, words and/or phrases) are decoded, and features found from those acoustic units. The features are then used with IR techniques (e.g., TF-IDF based retrieval) to obtain a target output (a word or words). Also described is the use of IR techniques to provide a full large vocabulary continuous speech (LVCSR) recognizer
摘要翻译： 描述了在语音识别（ASR）系统中使用信息检索（IR）技术的技术。 声学单元（例如，电话，音节，多电话单元，单词和/或短语）被解码，并且从那些声学单元找到的特征。 然后将特征与IR技术（例如，基于TF-IDF的检索）一起使用以获得目标输出（一个或多个单词）。 还描述了使用IR技术来提供完整的大词汇连续语音（LVCSR）识别器
-
2.发明申请公开(公告)号：US20130317820A1
公开(公告)日：2013-11-28
申请号：US13479945
申请日：2012-05-24
申请人： Xiaoqiang Xiao , Venkatesh Nagesha
发明人： Xiaoqiang Xiao , Venkatesh Nagesha
IPC分类号： G10L15/00
CPC分类号： G10L15/01 , G10L15/065
摘要： An automatic speech recognition dictation application is described that includes a dictation module for performing automatic speech recognition in a dictation session with a speaker user to determine representative text corresponding to input speech from the speaker user. A post-processing module develops a session level metric correlated to verbatim recognition error rate of the dictation session, and determines if recognition performance degraded during the dictation session based on a comparison of the session metric to a baseline metric.
摘要翻译： 描述了一种自动语音识别听写应用程序，其包括用于在与扬声器用户的听写会话中执行自动语音识别的听写模块，以从扬声器用户确定对应于输入语音的代表性文本。 后处理模块开发与听写会话的逐字识别错误率相关的会话级别度量，并且基于会话度量与基准度量的比较来确定在听写会话期间识别性能是否下降。
-
3.发明授权公开(公告)号：US09269349B2
公开(公告)日：2016-02-23
申请号：US13479945
申请日：2012-05-24
申请人： Xiaoqiang Xiao , Venkatesh Nagesha
发明人： Xiaoqiang Xiao , Venkatesh Nagesha
IPC分类号： G10L15/06 , G10L15/01 , G10L15/065
CPC分类号： G10L15/01 , G10L15/065
摘要： An automatic speech recognition dictation application is described that includes a dictation module for performing automatic speech recognition in a dictation session with a speaker user to determine representative text corresponding to input speech from the speaker user. A post-processing module develops a session level metric correlated to verbatim recognition error rate of the dictation session, and determines if recognition performance degraded during the dictation session based on a comparison of the session metric to a baseline metric.
摘要翻译： 描述了一种自动语音识别听写应用程序，其包括用于在与扬声器用户的听写会话中执行自动语音识别的听写模块，以从扬声器用户确定对应于输入语音的代表性文本。 后处理模块开发与听写会话的逐字识别错误率相关的会话级别度量，并且基于会话度量与基准度量的比较来确定在听写会话期间识别性能是否下降。
-
-
搜索结果
3 条记录 (耗时 0.025 秒)
