公开(公告)号：US20140122069A1

公开(公告)日：2014-05-01

申请号：US13663546

申请日：2012-10-30

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Seth E. Bravin ,  Brian J. Cragun ,  Robert A. Foyle ,  Ali Sobhi

IPC: G10L15/26

CPC classification number: G10L15/183

Abstract: A mechanism is provided for utilizing content analytics to automate corrections and improve speech recognition accuracy. A set of current corrected content elements is identified within a transcribed corrected media. Each current corrected content element in the set of current corrected content elements is weighted with an assigned weight based on one or more predetermined weighting conditions and a context of the transcribed corrected media. A confidence level is associated with each corrected content element based on the assigned weight. The set of current corrected content elements and the confidence level associated with each current corrected content element in a set of corrected elements is stored in a storage device for use in a subsequent transcription correction.

Abstract translation: 提供了一种利用内容分析来自动校正和提高语音识别精度的机制。 在转录的校正介质内识别出一组当前校正的内容元素。 基于一个或多个预定加权条件和转录的校正的媒体的上下文，对当前校正的内容元素组中的每个当前校正的内容元素进行加权。 基于分配的权重，置信水平与每个修正的内容元素相关联。 一组当前校正的内容元素和与一组校正元素中的每个当前校正的内容元素相关联的置信水平被存储在用于后续转录校正的存储设备中。

公开(公告)号：US20140122058A1

公开(公告)日：2014-05-01

申请号：US13663536

申请日：2012-10-30

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Seth E. Bravin ,  Brian J. Cragun ,  Ali Sobhi

IPC: G06F17/27

CPC classification number: G06F17/2725

Abstract: A mechanism is provided for subtractive transcript improvement. The mechanism identifies a set of corrections made to a previous transcript, where the set of corrections comprise, for each correction in the set of corrections, an erred phrase and a correction made to the erred phrase. For each erred phrase in a set of erred phrases in a current transcript, the mechanism determines whether the erred phrase in the current transcript matches an erred phrase in the set of corrections made to the previous transcript. Responsive to the erred phrase in the current transcript matching an erred phrase in the set of corrections made to the previous transcript, the mechanism corrects the erred phrase in the current transcript with the correction made to the erred phrase in the previous transcript.

Abstract translation: 提供减少转录本提高的机制。 该机制识别对前一记录进行的一组校正，其中对于校正集合中的每个校正，校正集包括错误的短语和对错误的短语进行的校正。 对于当前成绩单中的一组错误短语中的每个错误短语，该机制确定当前记录中的错误短语是否与对前一个记录集进行的更正集合中的错误短语匹配。 对于当前成绩单中错误的短语，与前一记录所做的修改中的错误短语相对应，该机制纠正了当前成绩单中错误的短语，并对上一个记录中错误的短语进行了更正。

公开(公告)号：US20150006708A1

公开(公告)日：2015-01-01

申请号：US13927458

申请日：2013-06-26

Applicant: International Business Machines Corporation

Inventor： Christine A. Banke ,  Peter J. Fay ,  Barry A. Feigenbaum ,  Mary Jo Mueller ,  Ali Sobhi ,  Elizabeth V. Woodward

IPC: H04L12/26

CPC classification number: H04L67/22 ,  G06Q30/02 ,  G06Q50/01 ,  H04W4/029

Abstract: Embodiments relate to determining the health of a network community. Aspects include defining, via a computer processor, measurable aspects associated with the network community. The measurable aspects include metrics for one or more of: quantified interactions among users in the network community, quantified activities among the users that are associated with a topic, and quantified activities indicative of network community accessibility. Aspects also include monitoring activities conducted via the network community, collecting data from monitored activities that correspond to the measurable aspects, and analyzing collected data from the monitored activities. The analyzing is performed as a function of the metrics. Aspects further include determining, via the computer processor, a health status of the network community from results of the analyzing.

Abstract translation: 实施例涉及确定网络社区的健康状况。 方面包括通过计算机处理器定义与网络社区相关联的可测量的方面。 可衡量的方面包括以下一个或多个的指标：网络社区中的用户之间的量化交互，与主题相关联的用户之间的量化活动以及指示网络社区可访问性的量化活动。 方面还包括通过网络社区进行的监测活动，从监测活动中收集与可衡量方面相对应的数据，并分析监测活动收集的数据。 根据指标进行分析。 方面还包括经由计算机处理器从分析结果确定网络社区的健康状况。