公开(公告)号：US09584946B1

公开(公告)日：2017-02-28

申请号：US15178602

申请日：2016-06-10

Applicant: Philip Scott Lyren ,  Glen A. Norris

Inventor： Philip Scott Lyren ,  Glen A. Norris

IPC: H04R5/02 ,  H04S7/00 ,  H04W88/02

CPC classification number: H04S7/30 ,  G10L15/04 ,  G10L25/81 ,  H04M1/0202 ,  H04M2201/40 ,  H04S7/302 ,  H04S2420/01 ,  H04W88/02

Abstract: Speech and/or non-speech in an audio input are convolved to localize sounds to different locations for a user. An audio diarization system segments the audio input into speech and non-speech segments. These segments are convolved with one or more head related transfer functions (HRTFs) so the sounds localize to different sound localization points (SLPs) for the user.

Abstract translation: 音频输入中的语音和/或非语音被卷积以将声音本地化为用户的不同位置。 音频二进制系统将音频输入分成语音和非语音段。 这些段与一个或多个与头相关的传递函数（HRTF）卷积，使得声音定位到用户的不同声音定位点（SLP）。

公开(公告)号：US20170047070A1

公开(公告)日：2017-02-16

申请号：US15339788

申请日：2016-10-31

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak

IPC: G10L15/30 ,  G10L15/193 ,  H04M3/51 ,  G10L13/08

CPC classification number: G10L15/30 ,  G10L13/08 ,  G10L15/18 ,  G10L15/193 ,  G10L15/32 ,  G10L15/34 ,  H04M3/51 ,  H04M3/5166 ,  H04M3/5183 ,  H04M2201/38 ,  H04M2201/40

Abstract: A computer-implemented system and method for performing distributed speech recognition is provided. Audio data is collected. A main grammar and secondary grammars are simultaneously provided for the audio data. Each secondary grammar includes an independent grammar. Speech recognition is simultaneously performed on the audio data using each secondary grammar. A new grammar is constructed for the audio data based on the main grammar template using results of the speech recognition. Further speech recognition is performed on the audio data using the new grammar.

Abstract translation: 提供了一种用于执行分布式语音识别的计算机实现的系统和方法。 收集音频数据。 同时为音频数据提供主语法和辅助语法。 每个二级语法包括一个独立的语法。 使用每个二级语法对音频数据同时执行语音识别。 基于使用语音识别结果的主语法模板为音频数据构建新的语法。 使用新的语法对音频数据进行进一步的语音识别。

公开(公告)号：US20170032790A1

公开(公告)日：2017-02-02

申请号：US15237583

申请日：2016-08-15

Applicant: Intellisist, Inc.

Inventor： Mike O. Webb ,  Bruce J. Peterson ,  Janet S. Kaseda

IPC: G10L15/26 ,  H04M3/533 ,  G10L15/04

CPC classification number: G10L15/26 ,  G10L15/04 ,  H04M3/53333 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/2016 ,  H04M2203/4536

Abstract: A computer-implemented system and method for efficient voice transcription is provided. A verbal message is processed by splitting the verbal message into segments and generating text for each of the segments via automated speech recognition. A confidence score is assigned to each text segment. The text segments are provided to workbenches, in order, staring with the text segment having a lowest confidence score. For at least one text segment provided to the workbench, one of edits to the text segment and manually transcribed text to replace the text segment are received. A threshold is applied to a time for performing the message processing and upon satisfaction of the threshold, the message processing is terminated. A text message is generated for the verbal message based on one of the generated text segment, manual transcription, or edited text segment for each of the text segments in that verbal message.

Abstract translation: 提供了一种用于高效语音转录的计算机实现的系统和方法。 通过将言语消息分割成段并通过自动语音识别为每个段生成文本来处理口头消息。 对每个文本段分配置信度分数。 将文本段提供给工作台，以便与具有最低置信度得分的文本段一起凝视。 对于提供给工作台的至少一个文本段，接收文本段的编辑和手动转录文本以替换文本段。 阈值被应用于执行消息处理的时间，并且在满足阈值时，终止消息处理。 基于该语言消息中的每个文本段的生成的文本段，手动转录或编辑的文本段之一，为语言消息生成文本消息。

公开(公告)号：US20170026515A1

公开(公告)日：2017-01-26

申请号：US15285373

申请日：2016-10-04

Applicant: Eric F. Bernstein

Inventor： Eric F. BERNSTEIN ,  Grant L. ALDRICH ,  Jasson GILMORE

IPC: H04M3/51 ,  G06Q10/02 ,  G10L15/08

CPC classification number: H04M3/5175 ,  G06Q10/02 ,  G10L15/26 ,  G10L25/48 ,  G10L2015/088 ,  H04M2201/40 ,  H04M2203/552

Abstract: There is disclosed a method in a data processing system for automatically and accurately determining an outcome of a phone call by using signifiers or audibles as a way to increase accuracy without altering the flow of the conversation. The disclosed method can be used in any call center, such as a high volume call center used in the financial (banking), insurance, rental (hotel or car), ticket sales, and the like. The method comprises receiving voice data of a phone call; transmitting a response communication based on the voice data, wherein the response communication includes at least one audible or signifier; identifying, by at least one processor, the at least one audible or signifier in the response communication; and automatically determining the outcome of the phone call based on the audible or signifier in the response communication. A data processing system and a non-transitory computer-readable medium for storing instructions consistent with the described method are also disclosed.

Abstract translation: 公开了一种数据处理系统中的方法，用于通过使用符号或听觉来自动和准确地确定电话呼叫的结果，作为提高准确度而不改变对话流程的方式。 所公开的方法可以用于任何呼叫中心，例如在金融（银行），保险，租赁（酒店或汽车），票务销售等中使用的大容量呼叫中心。 该方法包括：接收电话呼叫的语音数据; 发送基于所述语音数据的响应通信，其中所述响应通信包括至少一个听觉或符号; 通过至少一个处理器识别所述响应通信中的所述至少一个听觉或符号; 并且基于响应通信中的可听或者指示符来自动确定电话呼叫的结果。 还公开了一种用于存储与所述方法一致的指令的数据处理系统和非暂时计算机可读介质。

公开(公告)号：US09553985B2

公开(公告)日：2017-01-24

申请号：US13685987

申请日：2012-11-27

Applicant: Meir Cohen

Inventor： Meir Cohen

IPC: H04M3/42 ,  H04M3/436

CPC classification number: H04M3/4365 ,  H04M3/42059 ,  H04M3/436 ,  H04M2201/40 ,  H04M2203/2011 ,  H04M2203/2027 ,  H04M2203/6072

Abstract: Unwanted calls are detected by determining all calls which are unverified by prior prompting the caller to provide data, such as “press 5 to be connected” or “say ‘proceed’” before being allowed to connect. Once connected, the called party may indicate that the call was/is unwanted and should be disconnected. Then, the call is disconnected from the called party while being maintained with the switch. The call is also recorded in embodiments of the disclosed technology, with the audio therefrom, or audio signature, being used to detect future unwanted calls. The detection of future unwanted calls may further be modified or determined based on association of called parties to each other, which, additionally, may be used to change the threshold of closeness of audio signatures between calls.

Abstract translation: 通过先前提示呼叫者提供数据，例如“允许连接”按“5”或“说”继续进行“之前确定所有未被验证的呼叫，才能检测到不需要的呼叫。 一旦连接，被叫方可能会指示呼叫是/不需要的，应该断开连接。 然后，在通过交换机维护时，呼叫与被叫方断开连接。 呼叫也被记录在所公开的技术的实施例中，其中的音频或音频签名用于检测未来的不期望的呼叫。 可以基于被叫方对彼此的关联进一步修改或确定对未来不需要的呼叫的检测，另外可以用于改变呼叫之间的音频签名的接近阈值。

公开(公告)号：US09552417B2

公开(公告)日：2017-01-24

申请号：US14281323

申请日：2014-05-19

Applicant: Global Tel*Link Corp.

Inventor： Andreas M. Olligschlaeger ,  Jim Rokosky

IPC: H04M3/22 ,  G06F17/30 ,  H04M3/42 ,  G10L15/26

CPC classification number: G06F17/30563 ,  G06F17/30592 ,  G06F17/30746 ,  G06F17/30752 ,  G10L15/26 ,  H04M3/2281 ,  H04M3/42221 ,  H04M2201/40

Abstract: A system and method for the automated monitoring of inmate telephone calls as well as multi-modal search, retrieval and playback capabilities for said calls. A general term for such capabilities is multi-modal audio mining. The invention is designed to provide an efficient means for organizations such as correctional facilities to identify and monitor the contents of telephone conversations and to provide evidence of possible inappropriate conduct and/or criminal activity of inmates by analyzing monitored telephone conversations for events, including, but not limited to, the addition of third parties, the discussion of particular topics, and the mention of certain entities.

Abstract translation: 一种用于自动监测囚犯电话呼叫的系统和方法，以及用于所述呼叫的多模式搜索，检索和回放功能。 这种功能的一般术语是多模式音频挖掘。 本发明旨在为诸如惩教设施等组织识别和监测电话对话的内容提供有效的手段，并通过分析监测的电话对话来提供囚犯可能的不当行为和/或犯罪活动的证据，包括但不限于 不仅限于增加第三方，讨论特定主题以及提及某些实体。

公开(公告)号：US09544430B2

公开(公告)日：2017-01-10

申请号：US13504550

申请日：2010-10-27

Applicant: Michaela Nachtrab ,  Robin Ribback

Inventor： Michaela Nachtrab ,  Robin Ribback

IPC: G10L15/00 ,  G10L15/26 ,  G06F17/28 ,  H04M3/42 ,  G10L15/30 ,  G10L15/22 ,  H04N21/2343 ,  H04N21/81

CPC classification number: H04M3/42391 ,  G06F17/289 ,  G10L15/22 ,  G10L15/26 ,  G10L15/30 ,  G10L2015/225 ,  G10L2015/226 ,  H04M2201/40 ,  H04M2201/42 ,  H04M2201/60 ,  H04M2203/2061 ,  H04N21/234336 ,  H04N21/8106

Abstract: A method and system for transcription of spoken language into continuous text for a user comprising the steps of inputting spoken language of at least one user or of a communication partner of the at least one user into a mobile device of the respective user, wherein the input spoken language of the user is transported within a corresponding stream of voice over IP data packets to a transcription server; transforming the spoken language transported within the respective stream of voice over IP data packets into continuous text by means of a speech recognition algorithm run by said transcription server, wherein said speech recognition algorithm is selected depending on a natural language or dialect spoken in the area of the current position of said mobile device; and outputting said transformed continuous text forwarded by said transcription server to said mobile device of the respective user or to a user terminal of the respective user in real time.

Abstract translation: 一种用于将口语转录成用户的连续文本的方法和系统，包括以下步骤：将至少一个用户或至少一个用户的通信对方的口语输入到相应用户的移动设备中，其中输入 用户的语音在相应的IP数据包上的语音流中传送到转录服务器; 通过由所述转录服务器运行的语音识别算法将通过IP数据分组的各个语音流内传输的口语变换为连续文本，其中所述语音识别算法根据在所述语音识别算法的区域中所说的自然语言或方言来选择 所述移动设备的当前位置; 并且将由所述转录服务器转发的所述变换的连续文本实时地输出到相应用户的所述移动设备或相应用户的用户终端。

公开(公告)号：US09537993B1

公开(公告)日：2017-01-03

申请号：US15201681

申请日：2016-07-05

Applicant: West Corporation

Inventor： David Scheet ,  James K. Boutcher ,  Jeffrey William Cordell

IPC: H04M1/64 ,  H04M1/656 ,  H04M3/42 ,  H04M3/58 ,  H04M3/51 ,  H04M3/56 ,  G10L15/26 ,  G06F17/27

CPC classification number: H04M1/656 ,  G06F17/2705 ,  G06F17/2765 ,  G10L15/26 ,  H04M1/642 ,  H04M3/42221 ,  H04M3/5175 ,  H04M3/533 ,  H04M3/54 ,  H04M3/56 ,  H04M3/563 ,  H04M3/58 ,  H04M2201/18 ,  H04M2201/40 ,  H04M2203/301 ,  H04M2203/303 ,  H04M2203/559

Abstract: A method and apparatus of processing a voice call are disclosed. One example method of operation may include recording at least a portion of a voice call, and storing the portion of the voice call in memory. The method may also include processing the portion of the voice call to identify at least one segment of interest, and forwarding the at least one segment of interest to a new call party responsive to a call transfer action.

Abstract translation: 公开了一种处理语音呼叫的方法和装置。 一个示例性的操作方法可以包括记录语音呼叫的至少一部分，并将该部分语音呼叫存储在存储器中。 该方法还可以包括处理语音呼叫的一部分以识别感兴趣的至少一个段，以及响应于呼叫转移动作将该感兴趣的至少一个段转发到新的呼叫方。

公开(公告)号：US09531876B2

公开(公告)日：2016-12-27

申请号：US14270550

申请日：2014-05-06

Applicant: Avaya, Inc.

Inventor： Rodney A. Thomson

IPC: H04M3/00 ,  H04M5/00 ,  H04M3/51 ,  H04M3/42 ,  H04M3/20 ,  H04M7/00 ,  H04M1/656 ,  H04M1/65

CPC classification number: H04M3/51 ,  H04M1/651 ,  H04M1/656 ,  H04M3/20 ,  H04M3/42221 ,  H04M3/5175 ,  H04M3/5183 ,  H04M7/0042 ,  H04M2201/40 ,  H04M2203/301 ,  H04M2203/402 ,  H04M2203/552 ,  H04M2203/558

Abstract: Contact centers often record customer-agent communications for training, quality control, and other purposes. Supervisors often contribute to the communications in the form of voice messages only the agent can hear (e.g., whisper mode) and/or text messages displayed on a screen and optionally documents or other content that may be provided or shared by the supervisor to the agent. Capturing the supervisor's contribution to a communication is provided to enable later playback or review of the communication to include all inputs and enable a more complete understanding of the actions that were or were not taken.

Abstract translation: 联络中心通常会记录客户代理人的培训，质量控制和其他用途。 主管通常仅以代理人可以听到（例如，耳语模式）和/或显示在屏幕上的文本消息和可选的文档或其他可由主管向代理提供或共享的内容的语音消息形式进行通信。 。 捕获主管对通信的贡献是为了能够稍后播放或审查通信以包括所有输入，并且能够更全面地了解已经或未被采用的动作。

公开(公告)号：US20160371311A1

公开(公告)日：2016-12-22

申请号：US15253775

申请日：2016-08-31

Applicant: Nikhil Murgai

Inventor： Nikhil Murgai

IPC: G06F17/30 ,  G10L25/90 ,  H04M3/22 ,  G06F21/62

CPC classification number: G06F16/2228 ,  G06F16/258 ,  G06F16/61 ,  G06F21/6209 ,  G10L15/08 ,  G10L15/26 ,  G10L25/90 ,  H04M3/2218 ,  H04M3/51 ,  H04M3/5175 ,  H04M2201/40 ,  H04M2203/2038

Abstract: A system and method is provided for providing searchable customer call indexes. Consistent with disclosed embodiments, a system may receive call information associated with telephone conversations between callers and a vendor, the call information including an audio recording or transcript for each telephone conversation. The system may also identify one or more keywords from the audio recordings or transcripts and index the call information into one or more indexes based on the identified keywords. Finally, the system may determine search results responsive to a search query based on the indexing. In some embodiments, changes to customer service may be identified based on the search results.

Abstract translation: 提供了一种用于提供可搜索的客户呼叫索引的系统和方法。 与所公开的实施例一致，系统可以接收与呼叫者和供应商之间的电话对话相关联的呼叫信息，呼叫信息包括用于每个电话会话的音频记录或记录。 系统还可以从音频记录或成绩单中识别一个或多个关键字，并且基于所识别的关键字将呼叫信息索引到一个或多个索引中。 最后，系统可以基于索引确定响应于搜索查询的搜索结果。 在一些实施例中，可以基于搜索结果来识别对客户服务的改变。