FUNDAMENTAL FREQUENCY PATTERN GENERATION APPARATUS AND FUNDAMENTAL FREQUENCY PATTERN GENERATION METHOD

• US 20090070116A1
• Filed: 09/05/2008
• Published: 03/12/2009
• Est. Priority Date: 09/10/2007
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Mizutani, Nobuaki
• Granted Patent: US 8,478,595 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A fundamental frequency pattern generation apparatus includes a first storage including representative vectors each corresponding to a prosodic control unit and having a section for changing the number of phonemes, a second storage unit including a rule to select a vector corresponding to an input context, a selection unit configured to select a vector from the representative vectors by applying the rule to the context and output the selected vector, a calculation unit configured to calculate an expansion/contraction ratio of the section of the selected vector in a time-axis direction based on a designated value for a specific feature amount related to a length of a fundamental frequency pattern to be generated, the designated value of the feature amount being required of the fundamental frequency pattern to be generated, and an expansion/contraction unit configured to expand/contract the selected vector based on the expansion/contraction ratio to generate the fundamental frequency pattern.

Claims

1. A fundamental frequency pattern generation apparatus comprising:

a first storage unit to store a plurality of representative vectors each corresponding to a prosodic control unit and having a section for changing the number of phonemes;

a second storage unit to store a rule to select a representative vector corresponding to an input context;

a selection unit configured to select the representative vector corresponding to the input context from the plurality of representative vectors by applying the rule to the input context and output the selected representative vector;

a calculation unit configured to calculate an expansion/contraction ratio of the section of the selected representative vector in a time-axis direction based on a designated value for a specific feature amount related to a length of a fundamental frequency pattern to be generated, the designated value of the feature amount being required of the fundamental frequency pattern to be generated; and

an expansion/contraction unit configured to expand/contract the selected representative vector based on the expansion/contraction ratio to generate the fundamental frequency pattern.

2. The apparatus according to claim 1, wherein

the specific feature amount is a phoneme duration of the fundamental frequency pattern to be generated,

the calculation unit calculates an expansion/contraction ratio for a phoneme duration of the section of the selected representative vector based on the designated value of the phoneme duration, and

the expansion/contraction unit expands/contracts the duration of the section of the selected representative vector in accordance with the expansion/contraction ratio.

3. The apparatus according to claim 2, wherein the expansion/contraction unit expands/contracts, for each phoneme, a phoneme duration of the selected representative vector except the section in accordance with the designated value of the phoneme duration.

4. The apparatus according to claim 1, wherein

the specific feature amount is the number of phonemes of the fundamental frequency pattern to be generated,

the calculation unit calculates an expansion/contraction ratio for the number of phonemes of the section of the selected representative vector based on the designated value of the number of phonemes, and

the expansion/contraction unit expands/contracts the number of phonemes of the section of the selected representative vector in accordance with the expansion/contraction ratio and expands/contracts, for each phoneme, a duration of the selected representative vector in accordance with the designated value of a phoneme duration of the fundamental frequency pattern to be generated.

5. The apparatus according to claim 1, wherein the calculation unit calculates one of an expansion/contraction ratio sequence which monotonically increases from a start of the section and then monotonically decreases to an end of the section, and an expansion/contraction ratio sequence which monotonically decreases from the start of the section and then monotonically increases to the end of the section.

6. The apparatus according to claim 1, wherein the section is a section of the representative vector, which starts with one of an accent nucleus phoneme, an accent nucleus succeeding adjacent phoneme, and an accent nucleus succeeding second phoneme and ends with one of a prosodic control unit end phoneme, a prosodic control unit end preceding adjacent phoneme, and a prosodic control unit end preceding second phoneme.

7. The apparatus according to claim 6, wherein the representative vector includes the section as a first section, and a second section from a prosodic control unit start phoneme to one of an accent nucleus preceding adjacent phoneme, an accent nucleus phoneme, and an accent nucleus succeeding adjacent phoneme.

8. The apparatus according to claim 6, wherein the representative vector includes the section as a first section, a second section from a prosodic control unit start phoneme to one of an accent nucleus preceding adjacent phoneme, an accent nucleus phoneme, and an accent nucleus succeeding adjacent phoneme, and a third section from a succeeding adjacent phoneme to the first section to a prosodic control unit end phoneme.

9. The apparatus according to claim 1, wherein the prosodic control unit is at least one of a sentence unit, a breath group unit, an accent phrase unit, a morpheme unit, a word unit, a mora unit, a syllable unit, a phoneme unit, a semi-phoneme unit, a unit obtained by dividing one phoneme into a plurality of parts, and a unit formed by combining two or more of them.

10. The apparatus according to claim 1, wherein the context contains language information about the prosodic control unit, which is obtained by analyzing a text.

11. The apparatus according to claim 1, wherein the context contains a value of an arbitrary attribute.

12. The apparatus according to claim 11, wherein the attribute is at least one of information about prominence, information about an utterance style, information representing an intention, and information representing a mental attitude.

13. The apparatus according to claim 1, wherein the phoneme is at least one of a mora, syllable, phoneme, semi-phoneme, and a unit obtained by dividing one phoneme into a plurality of parts.

14. The apparatus according to claim 1, wherein the representative vector is at least one of a fundamental frequency pattern extracted from natural voice, an approximated fundamental frequency pattern obtained by approximating the fundamental frequency pattern, an quantized fundamental frequency pattern obtained by quantizing the fundamental frequency pattern extracted from the natural voice, and an approximated quantized fundamental frequency pattern obtained by approximating the quantized fundamental frequency pattern.

15. The apparatus according to claim 1, wherein the designated value for the specific feature amount is a value obtained from the input context.

16. The apparatus according to claim 1, wherein the designated value for the specific feature amount is a value obtained from input information different from the input context.

17. A fundamental frequency pattern generation method comprising:

preparing in advance a first storage to store a plurality of representative vectors each corresponding to a prosodic control unit and having a section for changing the number of phonemes,

preparing in advance a second storage unit to store a rule to select a representative vector corresponding to an input context,

selecting the representative vector corresponding to the input context from the plurality of representative vectors by applying the rule to the input context and outputting the selected representative vector;

calculating an expansion/contraction ratio of the section of the selected representative vector in a time-axis direction based on a designated value for a specific feature amount related to a length of a fundamental frequency pattern to be generated, the designated value of the feature amount being required of the fundamental frequency pattern to be generated; and

expanding/contracting the selected representative vector based on the expansion/contraction ratio to generate the fundamental frequency pattern.

18. A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps comprising:

preparing in advance a first storage to store a plurality of representative vectors each corresponding to a prosodic control unit and having a section for changing the number of phonemes,

preparing in advance a second storage unit to store a rule to select a representative vector corresponding to an input context,

selecting the representative vector corresponding to the input context from the plurality of representative vectors by applying the rule to the input context and outputting the selected representative vector;

calculating an expansion/contraction ratio of the section of the selected representative vector in a time-axis direction based on a designated value for a specific feature amount related to a length of a fundamental frequency pattern to be generated, the designated value of the feature amount being required of the fundamental frequency pattern to be generated; and

expanding/contracting the selected representative vector based on the expansion/contraction ratio to generate the fundamental frequency pattern.