公开(公告)号：US20150324436A1

公开(公告)日：2015-11-12

申请号：US14649762

申请日：2012-12-28

Applicant: HITACHI, LTD.

Inventor： Yusuke FUJITA ,  Nobuo NUKAGA ,  Shoji KODAMA

IPC: G06F17/30 ,  G06F7/24

CPC classification number: G06F16/254 ,  G06F7/24 ,  G06F16/284 ,  G06F16/93

Abstract: A data processing system holds metadata extraction dictionary information defining a condition for extracting metadata from a plurality of kinds of data and relevance dictionary information defining a condition for associating the metadata extracted from the plurality of kinds of data, extracts the metadata from the plurality of kinds of data on the basis of the metadata extraction dictionary information, extracts metadata from inputted data, associates the metadata extracted from the inputted data with the metadata extracted from the plurality of kinds of data on the basis of the relevance dictionary information, and outputs information indicating a relation of any combination of the plurality of kinds of data, the inputted data, and the metadata extracted from the plurality of kinds of data and the inputted data on the basis of a result of the association.

Abstract translation: 数据处理系统保存从定义用于关联从多种数据提取的元数据的条件的多种数据和相关词典信息中定义用于提取元数据的条件的元数据提取词典信息，从多种类型中提取元数据 基于元数据提取字典信息提取数据，从输入数据中提取元数据，将从输入数据提取的元数据与从多种数据中提取的元数据相关联，并输出指示 根据关联结果，从多种数据和输入数据中提取的多种数据，输入数据和元数据的任何组合的关系。

公开(公告)号：US20220254352A1

公开(公告)日：2022-08-11

申请号：US17595472

申请日：2020-08-31

Applicant: The Johns Hopkins University ,  Hitachi, Ltd.

Inventor： Yusuke FUJITA ,  Shinji WATANABE ,  Naoyuki KANDA ,  Shota HORIGUCHI

IPC: G10L17/18 ,  G10L17/04 ,  G06N3/04

Abstract: An audio analysis platform may receive a portion of an audio input, wherein the audio input corresponds to audio associated with a plurality of speakers. The audio analysis platform may process, using a neural network, the portion of the audio input to determine voice activity of the plurality of speakers during the portion of the audio input, wherein the neural network is trained using reference audio data and reference diarization data corresponding to the reference audio data. The audio analysis platform may determine, based on the neural network being used to process the portion of the audio input, a diarization output associated with the portion of the audio input, wherein the diarization output indicates individual voice activity of the plurality of speakers. The audio analysis platform may provide the diarization output to indicate the individual voice activity of the plurality of speakers during the portion of the audio input.

公开(公告)号：US20160171100A1

公开(公告)日：2016-06-16

申请号：US14907877

申请日：2013-09-11

Applicant: HITACHI, LTD.

Inventor： Yusuke FUJITA ,  Ryu TAKEDA ,  Naoyuki KANDA

IPC: G06F17/30 ,  H04M11/10 ,  H04M3/51 ,  G10L15/08

CPC classification number: G06F16/638 ,  G06F16/00 ,  G06F16/24578 ,  G06F16/64 ,  G10L15/00 ,  G10L15/08 ,  G10L15/10 ,  G10L15/26 ,  G10L25/63 ,  G10L2015/088 ,  H04M3/42221 ,  H04M3/51 ,  H04M11/10 ,  H04M2201/40 ,  H04M2203/301

Abstract: Provided is a voice search technology that can efficiently find and check a problematic call. To this end, a voice search system of the present invention includes a call search database that stores, for each of a reception channel and a transmission channel of each of a plurality of pieces of recorded call voice data, voice section sequences in association with predetermined keywords and time information. The call search database is searched based on an input search keyword, so that a voice section sequence that contains the search keyword is obtained. More specifically, the voice search system obtains, as a keyword search result, a voice section sequence that contains the search keyword and the appearance time thereof from the plurality of pieces of recorded call voice data, and obtains, based on the appearance time in the keyword search result, the start time of a voice section sequence of another channel immediately before the voice section sequence obtained as the keyword search result, and thus determines the start time as the playback start position for playing back the recorded voice. Then, the playback start position is output as a voice search result.

Abstract translation: 提供了可以有效地发现和检查有问题的呼叫的语音搜索技术。 为此，本发明的语音搜索系统包括呼叫搜索数据库，其针对多个记录呼叫语音数据中的每一个的接收信道和传输信道中的每一个存储声音部分序列，与预定的 关键字和时间信息。 基于输入搜索关键字搜索呼叫检索数据库，从而获得包含搜索关键词的语音段序列。 更具体地，语音搜索系统从多个记录的呼叫语音数据中获取包含搜索关键词和出现时间的语音段序列作为关键字搜索结果，并且基于在 关键词搜索结果，紧接在作为关键字搜索结果获得的语音段序列之前的另一个频道的语音段序列的开始时间，并且因此确定开始时间作为用于播放所记录的声音的重放开始位置。 然后，作为语音搜索结果输出回放开始位置。