TEXT-TO-SPEECH DEVICE, TEXT-TO-SPEECH METHOD, AND COMPUTER PROGRAM PRODUCT

• US 20150269927A1
• Filed: 03/11/2015
• Published: 09/24/2015
• Est. Priority Date: 03/19/2014
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yamasaki, Tomohiro, Shimizu, Yuji, Yajima, Makoto, Yamanaka, Noriko, Miyamura, Yuichi
• Granted Patent: US 9,570,067 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 13/10 Prosody rules derived from text; Stress or intonation
• CPC Class Codes: G10L 2013/083 Special characters, e.g. punctuation marks

Abstract

According to an embodiment, a text-to-speech device includes a receiver to receive an input text containing a peculiar expression; a normalizer to normalize the input text based on a normalization rule in which the peculiar expression, a normal expression of the peculiar expression, and an expression style of the peculiar expression are associated, to generate normalized texts; a selector to perform language processing of each normalized text, and select a normalized text based on result of the language processing; a generator generate a series of phonetic parameters representing phonetic expression of the selected normalized text; a modifier modifies a phonetic parameter in the normalized text corresponding to the peculiar expression in the input text based on a phonetic parameter modification method according to the normalization rule of the peculiar expression; and a output unit to output a phonetic sound synthesized using the series of phonetic parameters including the modified phonetic parameter.

Claims

1. A text-to-speech device comprising:

a receiver to receive an input text which contains a peculiar expression;

a normalizer to normalize the input text based on a normalization rule in which the peculiar expression, a normal expression for expressing the peculiar expression in a normal form, and an expression style of the peculiar expression are associated with one another, so as to generate one or more normalized texts;

a selector to perform language processing with respect to each of the normalized texts, and select a single normalized text based on result of the language processing;

a generator to generate a series of phonetic parameters representing phonetic expression of the single normalized text;

a modifier to modify a phonetic parameter in the normalized text corresponding to the peculiar expression in the input text based on a phonetic parameter modification method according to the normalization rule of the peculiar expression; and

an output unit to output a phonetic sound which is synthesized using the series of phonetic parameters including the modified phonetic parameter.

2. The device according to claim 1, wherein

the generator generates the series of phonetic parameters by selecting a synthesis unit from a synthesis unit dictionary, and

the modifier modifies the synthesis unit, which is selected by the generator, based on a phonetic parameter modification method according to the normalization rule of the peculiar expression.

3. The device according to claim 1, wherein

the generator generates the series of phonetic parameters from an acoustic parameter based on the hidden Markov model, and

the modifier modifies the acoustic parameter, which is selected by the generator, based on a phonetic parameter modification method according to the normalization rule of the peculiar expression.

4. The device according to claim 1, wherein the modifier modifies the phonetic parameter so as to change the fundamental frequency of the phonetic sound output by the output unit.

5. The device according to claim 1, wherein the modifier modifies the phonetic parameter so as to change length of each sound included in the phonetic sound output by the output unit.

6. The device according to claim 1, wherein the modifier modifies the phonetic parameter so as to change pitch of the phonetic sound output by the output unit.

7. The device according to claim 1, wherein the modifier modifies the phonetic parameter so as to change volume of the phonetic sound output by the output unit.

8. A text-to-speech method comprising:

receiving, by a receiver, an input text which contains a peculiar expression;

normalizing, by a normalizer, the input text based on a normalization rule in which the peculiar expression, a normal expression for expressing the peculiar expression in a normal form, and an expression style of the peculiar expression are associated with one another, so as to generate one or more normalized texts;

performing, by a selector, language processing with respect to each of the normalized texts, and selecting a single normalized text based on result of the language processing;

generating, by a generator, a series of phonetic parameters representing phonetic expression of the single normalized text;

modifying, by a modifier, a phonetic parameter in the normalized text corresponding to the peculiar expression in the input text based on a phonetic parameter modification method according to the normalization rule of the peculiar expression; and

outputting, by an output unit, a phonetic sound which is synthesized using the series of phonetic parameters including the modified phonetic parameter.

9. A computer program product comprising a computer readable medium including programmed instructions, wherein the instructions, when executed by a computer, cause the computer to function as:

a receiver to receive an input text which contains a peculiar expression;

a normalizer to normalize the input text based on a normalization rule in which the peculiar expression, a normal expression for expressing the peculiar expression in a normal form, and an expression style of the peculiar expression are associated with one another, so as to generate one or more normalized texts;

a selector to perform language processing with respect to each of the normalized texts, and select a single normalized text based on result of the language processing;

a generator to generate a series of phonetic parameters representing phonetic expression of the single normalized text;

a modifier to modify a phonetic parameter in the normalized text corresponding to the peculiar expression in the input text based on a phonetic parameter modification method according to the normalization rule of the peculiar expression; and

an output unit to output a phonetic sound which is synthesized using the series of phonetic parameters including the modified phonetic parameter.