Transcription support system and transcription support method

Patent metadata

Field	Value
Publication number	US-9489946-B2
Application number	US-201213420828-A
Country	US
Kind code	B2
Filing date	Mar 15, 2012
Priority date	Jul 26, 2011
Publication date	Nov 8, 2016
Grant date	Nov 8, 2016

Abstract

In an embodiment, a transcription support system includes: a first storage, a playback unit, a second storage, a text generating unit, an estimating unit, and a setting unit. The first storage stores the voice data therein; a playback unit plays back the voice data; and a second storage stores voice indices, each of which associates a character string obtained from a voice recognition process with voice positional information, for which the voice positional information is indicative of a temporal position in the voice data and corresponds to the character string. The text creating unit creates text; the estimating unit estimates already-transcribed voice positional information based on the voice indices; and the setting unit sets a playback starting position that indicates a position at which playback is started in the voice data based on the already-transcribed voice positional information.

First claim

What is claimed is:

1. A transcription support system comprising:
a first memory configured to store voice data therein;
a playback circuit configured to play back the voice data;
a second memory configured to store therein voice indices, each of which associates a character string obtained from a voice-recognition process with voice positional information, the voice positional information indicative of a temporal position in the voice data and corresponding to the character string; and
a processing circuit configured to
create text in response to an operation input of a user;
estimate already-transcribed voice positional information that indicates a temporal position at which the creation of the text is completed in the voice data based on the voice indices;
acquire playback voice positional information that indicates of a current position of the voice data that is being played back by the playback circuit;
calculate a delay amount based on the already-transcribed voice positional information and the playback voice positional information; the delay amount indicating how much the generation of the text is delayed compared to the playback of the voice data; and
variably control the playback of the playback circuit so as for the delay amount to fall within a predetermined range, wherein

the processing circuit specifies a character string that matches with a character string constituting the text created by the processing circuit out of a plurality of character strings included in the voice indices, and estimates the already-transcribed voice positional information from voice positional information corresponding to a character string matched with a last character string of the text out of specified character strings, and wherein
the processing circuit, when the delay amount is equal to or larger than a second threshold, controls the playback circuit to playback a voice portion that includes the voice in the voice data at maintained normal speed, and to playback a silent portion that does not include a voice in the voice data at a lower speed than a speed in a normal playback.

2. The system according to claim 1 , wherein
the processing circuit controls the playback circuit to temporarily stop the playback of the voice data at the current playback position when the delay amount is equal to or larger than a first threshold.

3. The system according to claim 1 , wherein
the processing circuit, when the delay amount is equal to or larger than a first threshold, controls the playback circuit
to issue a predetermined warning sound,
to return the playback position of the voice data to a position that the already-transcribed voice positional information indicates, and
to continue the playback.

4. The system according to claim 1 , wherein
the processing circuit, when the delay amount is equal to or larger than a second threshold, controls the playback circuit to playback the voice data lower than a speed of a normal playback.

5. A transcription support method comprising:
playing back voice data;
creating text in response to an operation input of a user;
estimating already-transcribed voice positional information indicative of a position at which the creation of the text is completed in the voice data based on voice indices each of which associates a character string obtained from a voice recognition process with voice positional information, the voice positional information indicative of a temporal position in the voice data and corresponding to the character string; and
acquiring playback voice positional information that indicates of a current position of the voice data that is being played back at the playing back of the voice data;
calculating a delay amount based on the already-transcribed voice positional information and the playback voice positional information; the delay amount indicating how much the generation of the text is delayed compared to the playing back of the voice data; and
variably controlling the playing back of the voice data so as for the delay amount to fall within a predetermined range, wherein
the estimating of the already transcribed voice positional information further includes,
specifying a character string that matches with a character string constituting the text created by the processing circuit out of a plurality of character strings included in the voice indices; and
estimating the already-transcribed voice positional information from voice positional information corresponding to a character string matched with a last character string of the text out of specified character strings, and wherein
when the delay amount is equal to or larger than a second threshold, the playing back of the voice data is controlled to playback a voice portion that includes the voice in the voice data at maintained normal speed, and to playback a silent portion that does not include a voice in the voice data at a lower speed than a speed in a normal playback.

Assignees

• Ueno Kouji
• Shimogori Nobuhiro
• Ikeda Tomoo
• Nisiyama Osamu
• Suzuki Hirokazu
• Nagao Manabu
• Toshiba Kk

Inventors

• Ueno Kouji
• Shimogori Nobuhiro
• Ikeda Tomoo
• Nisiyama Osamu
• Suzuki Hirokazu
• Nagao Manabu

Classifications

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L2015/221

  Announcement of recognition results · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G10L2015/225

  Feedback of the input speech · CPC title