Voice selection supporting device, voice selection method, and computer-readable recording medium

• US 9,812,119 B2
• Filed: 03/10/2016
• Issued: 11/07/2017
• Est. Priority Date: 09/20/2013
• Status: Active Grant

• Current Assignee: Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Inventors: Suzuki, Masaru, Hirano, Kaoru
• Primary Examiner(s): Han, Qi
• Application Number:
  US15/066,007
• Publication Number:
  US 20160189704A1
• Time in Patent Office: 607 Days
• Field of Search: 704260, 704258, 704266, 704263, 704268
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A voice selection supporting device according to an embodiment of the present invention includes an acceptance unit that accepts input of a text, an analysis knowledge storage unit that stores therein text analysis knowledge to be used for characteristic analysis for the input text, an analysis unit that analyzes a characteristic of the text by referring to the text analysis knowledge, a voice attribute storage unit that stores therein a voice attribute of each voice dictionary, an evaluation unit that evaluates similarity between the voice attribute of the voice dictionary and the characteristic of the text, and a candidate presentation unit that presents, based on the similarity, a candidate for the voice dictionary suitable for the text.

Claims

1. A voice selection supporting device comprising:

a memory; and

one or more processors configured to function as an acceptance unit, an analysis unit, an evaluation unit, a candidate presentation unit and a voice synthesis unit, wherein

the acceptance unit accepts input of a text;

the analysis unit performs a morphological analysis of the text and obtains an attribute of the text by referring to text analysis knowledge, the text analysis knowledge associating attributes with results of the morphological analysis for texts respectively;

the evaluation unit evaluates respective similarities between the voice attributes for the voice dictionaries and the obtained attribute of the text, each of the voice attributes indicating voice characteristics of a speaker for a voice synthesis, each of the voice dictionaries corresponding to the speaker for the voice synthesis;

the candidate presentation unit presents, based on the similarities, a candidate of the speaker from the voice dictionaries suitable for the text; and

the voice synthesis unit reads the text corresponding to the candidate of the speaker into synthesized voices.

2. The voice selection supporting device according to claim 1, wherein

the memory is configured to function as a dictionary storage unit;

and

the one or more processors is further configured to function as a voice synthesis unit, a selection acceptance unit and a result output unit,

the dictionary storage unit stores therein the voice dictionaries;

the voice synthesis unit converts, based on an instruction from a user, all or a part of the input text into a voice by using the presented candidate of the speaker, and presents the voice to the user;

the selection acceptance unit accepts a selection instruction for the voice dictionaries from the user; and

the result output unit that outputs the selection result.

3. The voice selection supporting device according to claim 2, wherein:

the memory is further configured to function as a history storage unit; and

the one or more processors are further configured to function as an update unit,

the history storage unit stores therein, as a selection history, the selection result received from the result output unit and the text; and

the update unit updates the voice attribute for the voice dictionaries based on the selection history stored in the history storage unit.

4. The voice selection supporting device according to claim 1, wherein

The memory is further configured to function as a voice attribute storage unit;

and

the voice attribute storage unit stores therein the voice attributes for the voice dictionaries in descending order of the similarities with respect to the text.

5. A voice selection method employed in a voice selection supporting device comprising the steps of:

accepting input of a text;

performing a morphological analysis of the text and obtaining an attribute of the text by referring to text analysis knowledge, the text analysis knowledge associating attributes with results of the morphological analysis for texts respectively;

evaluating respective similarities between voice attributes for voice dictionaries and the obtained attribute of the text, each of the voice attributes indicating voice characteristics of a speaker for a voice synthesis, each of the voice dictionaries corresponding to the speaker for the voice synthesis;

presenting, based on the similarities, a candidate of the speaker from the voice dictionaries suitable for the text; and

reading the text corresponding to the candidate of the speaker into synthesized voices.

6. A non-transitory computer-readable recording medium that stores therein a computer program, the computer program causing a computer to execute a voice selection method, the method comprising:

accepting input of a text;

performing a morphological analysis of the text and obtaining an attribute of the text by referring to text analysis knowledge, the text analysis knowledge associating attributes with results of the morphological analysis for texts respectively;

evaluating respective similarities between voice attributes for voice dictionaries and the obtained attribute of the text, each of the voice attributes indicating voice characteristics of a speaker for a voice synthesis, each of the voice dictionaries corresponding to the speaker for the voice synthesis;

presenting, based on the similarities, a candidate of the speaker from the voice dictionaries suitable for the text; and

reading the text corresponding to the candidate of the speaker into synthesized voices.