Text generator, text generating method, and computer program product

Patent metadata

Field	Value
Publication number	US-9460718-B2
Application number	US-201414206178-A
Country	US
Kind code	B2
Filing date	Mar 12, 2014
Priority date	Apr 3, 2013
Publication date	Oct 4, 2016
Grant date	Oct 4, 2016

Abstract

According to an embodiment, a text generator includes a recognizer, a selector, and a generation unit. The recognizer is configured to recognize an acquired sound and obtain recognized character strings in recognition units and confidence levels of the recognized character strings. The selector is configured to select at least one of the recognized character strings used for a transcribed sentence on the basis of at least one of a parameter about transcription accuracy and a parameter about a workload needed for transcription. The generation unit is configured to generate the transcribed sentence using the selected recognized character strings.

First claim

What is claimed is:

1. A text generator, comprising a computer including hardware, the computer being configured to control the text generator to at least:
recognize an acquired sound and obtain recognized character strings in recognition units and confidence levels of the recognized character strings;
select at least one of the recognized character strings used for a transcribed sentence on the basis of a parameter about a work condition of a transcription work designated by an operator; and
generate the transcribed sentence using the selected recognized character strings, wherein
the computer is further configured to control the text generator to select the recognized character string on the basis of a combination of at least one of a parameter about transcription accuracy and a parameter about a workload needed for transcription with a confidence level of the recognized character string, and
the computer is further configured to control the text generator to use a transcription work time as the parameter about the workload needed for transcription, calculate the transcription work time of each of the recognized character strings on the basis of the number of characters of the recognized character string, compare an accumulated work time cumulatively showing the calculated transcription work time of the recognized character strings in descending order of the confidence levels thereof with an allowable value of the transcription work time, and select the recognized character string when the accumulated work time is equal to or smaller than the allowable value.

2. A text generator, comprising a computer including hardware, the computer being configured to control the text generator to at least:
recognize an acquired sound and obtain recognized character strings in recognition units and confidence levels of the recognized character strings;
select at least one of the recognized character strings used for a transcribed sentence on the basis of a parameter about a work condition of a transcription work designated by an operator; and
generate the transcribed sentence using the selected recognized character strings, wherein
the computer is further configured to control the text generator to select the recognized character string on the basis of a combination of at least one of a parameter about transcription accuracy and a parameter about a workload needed for transcription with a confidence level of the recognized character string, and
the computer is further configured to control the text generator to obtain a start time and an end time of each of the recognized character strings, and use a transcription work time as the parameter about the workload needed for transcription, calculate the transcription work time of each of the recognized character strings on the basis of the start time and the end time thereof, compare an accumulated work time cumulatively showing the calculated transcription work time of the recognized character strings in descending order of the confidence levels thereof with an allowable value of the transcription work time, and select the recognized character string when the accumulated work time is equal to or smaller than the allowable value.

3. A text generator, comprising a computer including hardware, the computer being configured to control the text generator to at least:
recognize an acquired sound and obtain recognized character strings in recognition units and confidence levels of the recognized character strings;
select at least one of the recognized character strings used for a transcribed sentence on the basis of a parameter about a work condition of a transcription work designated by an operator; and
generate the transcribed sentence using the selected recognized character strings, wherein
the computer is further configured to control the text generator to select the recognized character string on the basis of a combination of at least one of a parameter about transcription accuracy and a parameter about a workload needed for transcription with a confidence level of the recognized character string, and
the computer is further configured to control the text generator to use a transcription work cost as the parameter about the workload needed for transcription, calculate a transcription work time of each of the recognized character strings on the basis of the number of characters of the recognized character string, calculate the transcription work cost of each of the recognized character strings on the basis of the calculated transcription work time and a work cost per unit time, compare an accumulated work cost cumulatively showing the calculated transcription work cost of the recognized character strings in descending order of the confidence levels thereof with an allowable value of the transcription work cost, and select the recognized character string when the accumulated work cost is equal to or smaller than the allowable value.

4. A text generator, comprising a computer including hardware, the computer being configured to control the text generator to at least:
recognize an acquired sound and obtain recognized character strings in recognition units and confidence levels of the recognized character strings;
select at least one of the recognized character strings used for a transcribed sentence on the basis of a parameter about a work condition of a transcription work designated by an operator; and
generate the transcribed sentence using the selected recognized character strings, wherein
the computer is further configured to control the text generator to select the recognized character string on the basis of a combination of at least one of a parameter about transcription accuracy and a parameter about a workload needed for transcription with a confidence level of the recognized character string, and
the computer is further configured to control the text generator to:
obtain a start time and an end time of each of the recognized character strings, and
use a transcription work cost as the parameter about the workload needed for transcription, calculate a transcription work time of each of the recognized character strings on the basis of the start time and the end time of the recognized character string, calculate the transcription work cost of each of the recognized character strings on the basis of the calculated transcription work time and a work cost per unit time, compare an accumulated work cost cumulatively showing the calculated transcription work cost of the recognized character strings in descending order of the confidence levels thereof with an allowable value of the transcription work cost, and select the recognized character string when the accumulated work cost is equal to or smaller than the allowable value.

Assignees

• Toshiba Kk

Inventors

• Ashikawa Taira
• Nishiyama Osamu
• Ikeda Tomoo
• Ueno Koji
• Nakata Kouta

Classifications

• G10L15/26 Primary

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

• G10L2015/226

  using non-speech characteristics · CPC title

• G10L15/01

  Assessment or evaluation of speech recognition systems · CPC title