公开(公告)号：US20040158465A1

公开(公告)日：2004-08-12

申请号：US10770421

申请日：2004-02-04

申请人： CANNON KABUSHIKI KAISHA

发明人： David Llewellyn Rees

IPC分类号： G10L015/00

CPC分类号： G10L25/78 ,  G10L15/04

摘要： An apparatus is provided for detecting the presence of speech within an input speech signal. Speech is detected by treating the average frame energy of an input speech signal as a sampled signal and looking for modulations within the sampled signal that are characteristic of speech.

公开(公告)号：US20040153321A1

公开(公告)日：2004-08-05

申请号：US10748105

申请日：2003-12-31

申请人： Samsung Electronics Co., Ltd.

发明人： Seung-Nyung Chung ,  Myung-Hyun Yoo ,  Jay-Woo Kim ,  Joon-Ah Park

IPC分类号： G10L015/00

CPC分类号： G10L15/22

摘要： A method and apparatus for enhancing the performance of speech recognition by adaptively changing a process of determining the final, recognized word depending on a user's selection in a list of alternative words represented by a result of speech recognition. A speech recognition method comprising: inputting speech uttered by a user; recognizing the input speech and creating a predetermined number of alternative words to be recognized in the order of similarity; and displaying a list of alternative words arranged in a predetermined order and determining an alternative word that a cursor currently indicates as the final, recognized word if a user's selection from the list of alternative words has not been changed within a predetermined standby time.

摘要翻译： 一种用于通过根据由语音识别结果表示的替换词列表中的用户选择自适应地改变确定最终识别词的处理来增强语音识别性能的方法和装置。 一种语音识别方法，包括：输入用户发出的语音; 识别输入语音，并以相似性的顺序创建要被识别的预定数量的替代单词; 以及显示以预定顺序排列的备选单词的列表，并且如果来自替代单词列表的用户的选择在预定待机时间内没有改变，则确定光标当前指示为最终识别词的替代单词。

公开(公告)号：US20040153320A1

公开(公告)日：2004-08-05

申请号：US10472366

申请日：2004-03-25

发明人： Ihab Nahkla ,  Brett Andrew Avery ,  Eldon Chun-Keung Wong

IPC分类号： G10L015/00 ,  H04L012/66

CPC分类号： H04M3/42 ,  H04L29/06 ,  H04L41/0654 ,  H04L43/0811 ,  H04L67/14 ,  H04L69/329 ,  H04M3/002 ,  H04M3/2227 ,  H04M3/51 ,  H04M3/56 ,  H04M7/006 ,  H04M2201/16 ,  H04M2203/2027 ,  H04M2203/6045

摘要： Method of confirming the establishment of a voice connection, such as a VoIP connection, between first and second end stations coupled to a packet switched communications network. The voice connection is used to transfer an audible request from the first end station to the second end station, to ask the user of the second end station to generate a predetermined vocal response. The first end station compares any response from the second end station to the predetermined vocal response. The connection is determined to be established in response to a successful comparison. The predetermined vocal response includes a predetermined speech sequence comprising characters, a word or words, and a speech recognition procedure is applied to the received response to determine the presence of any speech sequence for comparison with the predetermined sequence. If a fault is detected an alternative connection is established to execute a process to correct the fault.

摘要翻译： 确定在耦合到分组交换通信网络的第一和第二终端站之间建立诸如VoIP连接的语音连接的方法。 语音连接用于将来自第一终端站的可听请求传送到第二终端站，以询问第二终端站的用户产生预定的声音响应。 第一终端站将来自第二终端站的任何响应与预定的声音响应进行比较。 确定连接是为了响应于成功的比较而建立的。 预定的声音响应包括包括字符，一个或多个单词的预定语音序列，并且将语音识别过程应用于所接收的响应，以确定任何语音序列的存在，以便与预定序列进行比较。 如果检测到故障，则建立替代连接以执行纠正故障的过程。

公开(公告)号：US20040117182A1

公开(公告)日：2004-06-17

申请号：US10472897

申请日：2003-09-25

发明人： Simon N Downey

IPC分类号： G10L015/00

CPC分类号： G10L15/08 ,  G10L15/22 ,  G10L2015/085 ,  G10L2015/228 ,  H04M3/4931 ,  H04M3/4936 ,  H04M2201/40

摘要： In this invention vocabulary size of a speech recognizer for a large task is reduced by providing a recognizer only for the most common vocabulary items. Uncommon items are catered for by providing aliases from the common items. This allows accuracy to remain high while also allowing uncommon items to be recognized when necessary.

摘要翻译： 在本发明中，通过仅为最常见的词汇项提供识别器来减少用于大任务的语音识别器的词汇大小。 通过提供通用项目中的别名来满足不寻常的项目。 这使得准确度保持较高，同时还允许在必要时识别不常见的项目。

公开(公告)号：US20040111259A1

公开(公告)日：2004-06-10

申请号：US10317837

申请日：2002-12-10

发明人： Edward S. Miller ,  James F. Blake II ,  Kyle N. Danielson ,  Michael D. Bergman ,  Keith C. Herold

IPC分类号： G10L015/00

CPC分类号： G10L15/19 ,  G10L2015/228

摘要： A system and method for a speech recognition system application program interface (API). The system and method additionally enable the application programmer to generate multiple grammars and voice channels, such that the audio data in any voice channel may be decoded utilizing any active grammar. The system and method enable the dynamic updating of grammars without reloading or rebooting the system. Additionally, the grammar can be implemented to include multiple grammars having multiple concepts. Still further, each concept can be implemented to include multiple phrases, and the system and method are configured to decode flexible phrase formats.

摘要翻译： 一种用于语音识别系统应用程序接口（API）的系统和方法。 该系统和方法还使得应用程序员能够产生多个语法和语音信道，使得任何语音信道中的音频数据可以利用任何活动语法进行解码。 系统和方法可以动态更新语法，而无需重新加载或重新启动系统。 另外，语法可以被实现为包括具有多个概念的多个语法。 此外，每个概念可以被实现为包括多个短语，并且系统和方法被配置为解码灵活的短语格式。

公开(公告)号：US20040083099A1

公开(公告)日：2004-04-29

申请号：US10687703

申请日：2003-10-20

发明人： Robert Scarano ,  Lawrence Mark

IPC分类号： G10L015/00

CPC分类号： G10L15/08 ,  G06F17/30746 ,  G10L15/02 ,  H04M2201/40 ,  H04M2203/301

摘要： The present invention provides an audio analysis intelligence tool that provides ad-hoc search capabilities using spoken words as an organized data form. The present invention provides an SQL like interface to process and search audio data and combine it with other traditional data forms.

摘要翻译： 本发明提供一种音频分析智能工具，其使用口语单词作为有组织的数据形式来提供临时搜索能力。 本发明提供了一种SQL接口，用于处理和搜索音频数据并将其与其他传统数据形式相结合。

公开(公告)号：US20040073426A1

公开(公告)日：2004-04-15

申请号：US10450086

申请日：2003-11-05

发明人： Thomas Jung

IPC分类号： G10L015/00

CPC分类号： G11B27/107 ,  G11B20/12 ,  G11B27/11 ,  G11B2020/10546 ,  G11B2220/65

摘要： A method for storing acoustic information is described, characterized in that the information to be stored is combined into groups, and each group of information to be stored is assigned a group identifier characterizing that particular group, as well as a method for selecting information stored by the method according to the present invention, said information being characterized in that after input of a group identifier, preferably voice input via a microphone, a particular group of information is selected. The present invention permits a particularly rapid means of retrieving and selecting voice information stored in a voice memory.

摘要翻译： 描述了一种用于存储声信息的方法，其特征在于，要存储的信息被组合成组，并且将要存储的每组信息分配给表征该特定组的组标识符，以及用于选择由 根据本发明的方法，所述信息的特征在于，在输入组标识符之后，优选地经由麦克风的语音输入，选择特定的一组信息。 本发明允许检索和选择存储在语音存储器中的语音信息的特别快速的方法。

公开(公告)号：US20040059575A1

公开(公告)日：2004-03-25

申请号：US10269269

申请日：2002-10-10

发明人： John R. Brookes ,  Norikazu Endo

IPC分类号： G10L015/00

CPC分类号： G10L15/08 ,  G10L15/183

摘要： A multiple pass speech recognition method includes a first pass and a second pass. The first pass recognizes an input speech signal to generate a first pass result. The second pass generates a first grammar having a portion set to match a first part of the input speech signal, based upon the context of the first pass result, and generate a second pass result. The method may further include a third pass grammar limiting the second part of the input speech signal to the second pass result. The third pass grammar includes a model corresponding to the first part of the input speech signal and varying within the second pass result. The third pass compares the first part of the input speech signal to the model while limiting the second part of the input speech signal to the second pass result.

摘要翻译： 多次语音识别方法包括第一遍和第二遍。 第一遍识别输入语音信号以产生第一遍的结果。 基于第一遍结果的上下文，第二遍产生具有被设置为匹配输入语音信号的第一部分的部分的第一语法，并且生成第二遍结果。 该方法还可以包括将输入语音信号的第二部分限制到第二遍结果的第三遍语法。 第三遍语法包括对应于输入语音信号的第一部分并在第二遍结果内变化的模型。 第三遍将输入语音信号的第一部分与模型进行比较，同时将输入语音信号的第二部分限制到第二遍结果。

公开(公告)号：US20040059573A1

公开(公告)日：2004-03-25

申请号：US10644886

申请日：2003-08-19

发明人： Hwajin Cheong

IPC分类号： G10L015/00

CPC分类号： G10L21/0272 ,  G10L15/20

摘要： A voice command identifier for a voice recognition system is disclosed. In one aspect of the invention, the voice command identifier can selectively identify and recognize a user voice command received along with the background sound generated from the speaker of a device being controlled.

摘要翻译： 公开了一种用于语音识别系统的语音命令标识符。 在本发明的一个方面，语音命令标识符可以选择性地识别并识别接收到的用户语音命令以及从被控制的设备的扬声器产生的背景声音。

公开(公告)号：US20040044531A1

公开(公告)日：2004-03-04

申请号：US10380382

申请日：2003-09-05

发明人： Nikola Kirilov Kasabov ,  Waleed Habib Abdulla

IPC分类号： G10L015/00

CPC分类号： G10L15/197 ,  G10L15/142

摘要： The invention provides a method of speech recognition comprising the steps of receiving a signal comprising one or more spoken words, extracting a spoken word from the signal using a Hidden Markov Model, passing the spoken word to a plurality of word models, one or more of the word models based on a Hidden Markov Model, determining the word model most likely to represent the spoken word, and outputting the word model representing the spoken word. The invention also provides a related speech recognition system and a speech recognition computer program.

摘要翻译： 本发明提供了一种语音识别方法，包括以下步骤：接收包括一个或多个口语单词的信号，使用隐马尔可夫模型从该信号中提取口语单词，将口语单词传递到多个单词模型，一个或多个单词模型 基于隐马尔可夫模型的单词模型，确定最有可能表示口语单词的单词模型，并输出表示口语单词的单词模型。 本发明还提供了一种相关的语音识别系统和语音识别计算机程序。