Method, apparatus and program capable of outputting response perceivable to a user as natural-sounding

• US 10,224,021 B2
• Filed: 07/02/2015
• Issued: 03/05/2019
• Est. Priority Date: 07/02/2014
• Status: Active Grant

• Current Assignee: Yamaha Corporation
• Original Assignee: Yamaha Corporation
• Inventors: Matsubara, Hiroaki
• Primary Examiner(s): Shah, Paras D
• Assistant Examiner(s): Ogunbiyi, Oluwadamilola M
• Application Number:
  US15/316,850
• Publication Number:
  US 20170116978A1
• Time in Patent Office: 1,342 Days
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/56 Natural language generation
• 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 13/047 Architecture of speech synthesisers
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A voice synthesizing apparatus includes: a voice inputter (102) configured to input a voice; an obtainer (22) configured to obtain a primary response to the voice inputted by the voice inputter (102); an analyzer (112) configured to analyze whether the primary response includes a repetition target; and a voice synthesizer (24) configured to, in a case where the analyzed primary response is determined to include the repetition target, synthesize a voice from a secondary response that includes the repetition target repeated at least twice to output the voice.

Claims

1. A voice processing apparatus comprising:

at least one processor configured to execute stored instructions to;

receive an inputted voice from a user and perform language analysis on the inputted voice;

obtain a primary response data representative of a response to the inputted voice from a database;

analyze whether the primary response data includes an interjection with 2 or less syllables, wherein the interjection is included in a repetition target;

in a case where the analyzed primary response data is determined to include the interjection with 2 or less syllables, generate a voice sequence from a secondary response data that includes the repetition target repeated at least twice;

synthesize a voice based on the voice sequence; and

output the synthesized voice in digital form that includes the secondary response data.

2. The voice processing apparatus according to claim 1,

wherein the at least one processor is configured to:

in obtaining the primary response data, analyze a meaning of the inputted voice, and generate the primary response data as a response to the analyzed meaning.

3. The voice processing apparatus according to claim 1,

wherein the at least one processor is further configured to:

in a case where the number of syllables in the interjection included in the primary response data is 3 or more, output the primary response data as the secondary response data.

4. The voice processing apparatus according to claim 3,

wherein the at least one processor is further configured to:

generate a voice sequence from the secondary response data; and

synthesize a voice based on the voice sequence.

5. The voice processing apparatus according to claim 2,

wherein the voice processing apparatus is operable in a first mode or in a second mode,

wherein the at least one processor is configured to, in generating the primary response data, in the first mode, generate the primary response data in which an interjection and specific content are included, and in the second mode, generate the primary response data that includes either an interjection alone or the specific content alone.

6. The voice processing apparatus according to claim 3,

wherein the voice processing apparatus is operable in a prohibition mode,

wherein the at least one processor is configured to, in the prohibition mode, generate the secondary response data without an interjection with 2 or less syllables being repeated.

7. The voice processing apparatus according to claim 4,

wherein the voice processing apparatus is operable in a prohibition mode,

wherein the at least one processor is configured to, in the prohibition mode, generate the secondary response data without an interjection with 2 or less syllables being repeated.

8. The voice processing apparatus according to claim 5,

wherein the voice processing apparatus is operable in a prohibition mode,

wherein the at least one processor is configured to, in the prohibition mode, generate the secondary response data without an interjection with 2 or less syllables being repeated.

9. The voice processing apparatus according to claim 1, wherein the repetition target is one of a plurality of words that are pre-stored.

10. A voice processing method comprising:

receiving, by at least one processor, an inputted voice from a user and perform language analysis on the inputted voice;

obtaining, by the at least one processor, a primary response data representative of a response to the inputted voice from a database;

analyzing, by the at least one processor, whether the primary response data includes an interjection with 2 or less syllables, wherein the interjection is included in a repetition target;

in a case where the analyzed primary response data is determined to include the interjection with 2 or less syllables, generating a voice sequence from a secondary response data that includes the repetition target repeated at least twice;

synthesizing, by the at least one processor, a voice based on the voice sequence; and

outputting the synthesized voice in digital form that includes the secondary response data.

11. A non-transitory computer readable medium storing executable instructions, the executable instructions when executed by at least one processor performs a voice processing method, the method comprising:

receiving an inputted voice from a user and perform language analysis on the inputted voice;

obtaining a primary response data representative of a response to the inputted voice from a database;

analyzing whether the primary response data includes an interjection with 2 or less syllables, wherein the interjection is included in a repetition target;

in a case where the analyzed primary response data is determined to include the interjection with 2 or less syllables, generating a voice sequence from a secondary response data that includes the repetition target repeated at least twice;

synthesizing a voice based on the voice sequence; and

outputting the synthesize voice in digital form that includes the secondary response data.