Voice Search System, Voice Search Method, and Computer-Readable Storage Medium

Patent metadata

Field	Value
Publication number	US-2016171100-A1
Application number	US-201314907877-A
Country	US
Kind code	A1
Filing date	Sep 11, 2013
Priority date	Sep 11, 2013
Publication date	Jun 16, 2016
Grant date	—

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.

First claim

1 . A voice search system comprising:
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; and a processor configured to search the call search database based on an input search keyword, and obtain a voice section sequence that contains the search keyword, wherein the processor is configured to:
obtain, as a keyword search result, a voice section sequence that contains the search keyword and an appearance time of the voice section sequence from the plurality of pieces of recorded call voice data,
obtain, based on the appearance time in the keyword search result, a start time of a voice section sequence of another channel immediately before the voice section sequence obtained as the keyword search result, and determine the start time as a playback start position for playing back the recorded voice, and
output the playback start position as a voice search result.

2 . The voice search system according to claim 1 ,
wherein the call search database further stores a non-verbal information score of each voice section sequence, and the processor is configured to determine, based on the non-verbal information score, a priority of the voice search result for which the playback start position has been determined.

3 . The voice search system according to claim 2 , wherein the processor is configured to generate a search result display screen for presenting voice search results to a user by sorting the results in descending order of the priority, and display the search result display screen on a display device.

4 . The voice search system according to claim 3 , wherein the processor is configured to generate the search result display screen so as to allow, other than the start time of the voice section sequence of the other channel immediately before the voice section sequence obtained as the keyword search result, the start time of the voice section sequence obtained as the keyword search result or a start time of a voice section sequence of another channel immediately after the voice section sequence obtained as the keyword search result, to be selected as a playback start position for playing back the recorded voice, and display the playback start position on the display device.

5 . The voice search system according to claim 2 , wherein
the non-verbal information score is an emotion score that is obtained by determining an emotion in the voice section sequence, and the emotion score is associated with a start time of the voice section sequence.

6 . A voice search method for searching a call search database based on an input search keyword, and obtaining a voice section sequence that contains the search keyword, the call search database being configured to store, for each of a reception channel and a transmission channel of each of a plurality of pieces of call voice data, voice section sequences in association with predetermined keywords and time information, the method comprising causing a processor to:
obtain, as a keyword search result, a voice section sequence that contains the search keyword and an appearance time of the voice section sequence from the plurality of pieces of recorded call voice data; obtain, based on the appearance time in the keyword search result, a start time of a voice section sequence of another channel immediately before the voice section sequence obtained as the keyword search result, and determine the start time as a playback start position for playing back the recorded voice; and output the playback start position as a voice search result.

7 . The voice search method according to claim 6 , wherein
the call search database further stores a non-verbal information score of each voice section sequence, and the method further comprises causing the processor to determine, based on the non-verbal information score, a priority of the voice search result for which the playback start position has been determined.

8 . The voice search method according to claim 7 , further comprising causing the processor to generate a search result display screen for presenting voice search results to a user by sorting the results in descending order of the priority, and display the search result display screen on a display device.

9 . The voice search method according to claim 8 , further comprising, in the step of displaying the search result display screen, causing the processor to generate the search result display screen so as to allow, other than the start time of the voice section sequence of the other channel immediately before the voice section sequence obtained as the keyword search result, the start time of the voice section sequence obtained as the keyword search result or a start time of a voice section sequence of another channel immediately after the voice section sequence obtained as the keyword search result, to be selected as a playback start position for playing back the recorded voice, and display the playback start position on the display device.

10 . The voice search method according to claim 7 , wherein
the non-verbal information score is an emotion score that is obtained by determining an emotion in the voice section sequence, and the emotion score is associated with a start time of the voice section sequence.

11 . A computer-readable storage medium that stores a program for causing a computer to execute the voice search method according to claim 6 .

Assignees

• Hitachi Ltd

Inventors

• Fujita Yusuke
• Takeda Ryu
• Kanda Naoyuki

Classifications

• G06F16/638 Primary

  Presentation of query results · CPC title

• H04M3/51

  Centralised call answering arrangements requiring operator intervention {, e.g. call or contact centers for telemarketing} · CPC title

• G06F16/64

  Browsing; Visualisation therefor (generation of a list or set of audio data G06F16/638) · CPC title

• G10L25/63

  for estimating an emotional state · CPC title

• G06F16/24578

  using ranking · CPC title