Speech synthesis apparatus

• US 6,499,014 B1
• Filed: 03/07/2000
• Issued: 12/24/2002
• Est. Priority Date: 04/23/1999
• Status: Expired due to Term

• Current Assignee: Rakuten, Inc. (Rakuten Group, Inc.)
• Original Assignee: OKI Electric Industry Company Limited
• Inventors: Chihara, Keiichi
• Primary Examiner(s): {haeck over (S)}mits, Ta̅livaldis Ivars
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US09/521,449
• Time in Patent Office: 1,022 Days
• Field of Search: 704/258, 704/260, 704/264, 704/266, 704/267, 704/268, 704/269
• US Class Current: 704/260
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

The speech synthesis apparatus of the present invention includes: a text analyzer operable to generate a phonetic and prosodic symbol string from character information of an input text; a word dictionary storing a reading and an accent of a word; an voice segment dictionary storing a phoneme that is a basic unit of speech; a parameter generator operable to generate synthesizing parameters including at least a phoneme, a duration of the phoneme and a fundamental frequency for the phonetic and prosodic symbol string, the parameter generator including a calculating means operable to obtain a sum of phrase components and a sum of accent components and to calculate an average pitch from the sum of the phrase components and the sum of the accent components, and a determining means operable to determine a base pitch from the average pitch; and a waveform generator operable to generate a synthesized waveform by making waveform-overlapping referring to the synthesizing parameters generated by the parameter generator and the voice segment dictionary.

Claims

1. A speech synthesis apparatus comprising:

a text analyzer operable to generate a phonetic and prosodic symbol string from character information of an input text;

a word dictionary storing a reading and an accent of a word;

a voice segment dictionary storing a phoneme that is a basic unit of speech;

a parameter generator operable to generate synthesizing parameters including at least a phoneme, a duration of the phoneme and a fundamental frequency for the phonetic and prosodic symbol string, the parameter generator including a calculating means operable to obtain a sum of phrase components and a sum of accent components and to calculate a mora average from the sum of the phrase components and the sum of the accent components, and a determining means operable to determine a base pitch from the mora average; and

a waveform generator operable to generate a synthesized waveform by making waveform-overlapping referring to the synthesizing parameters generated by the parameter generator and the voice segment dictionary.

2. A speech synthesis apparatus according to claim 1, wherein the calculating means calculates the mora average based on creation times and magnitudes of the respective phrase commands, start times, end times and magnitudes of the respective accent commands, and

the determining means determines the base pitch in such a manner that a value obtained by adding the mora average and the base pitch becomes constant.

3. A speech synthesis apparatus comprising:

a text analyzer operable to generate a phonetic and prosodic symbol string from character information of an input text;

a word dictionary storing a reading and an accent of a word;

a voice segment dictionary storing a phoneme that is a basic unit of speech;

a parameter generator operable to generate synthesizing parameters including at least a phoneme, a duration of the phoneme and a fundamental frequency for the phonetic and prosodic symbol string, the parameter generator including a calculating means operable to overlap a phrase component and an accent component, obtain an approximation of a pitch contour from the overlapped phrase and accent components and calculate at least a maximum value of the approximation of the pitch contour, and a modifying means operable to modify a value of the phrase component and a value of the accent component by using at least the maximum value; and

a waveform generator operable to generate a synthesized waveform by making waveform-overlapping referring to the synthesizing parameters generated by the parameter generator and the voice segment dictionary.

4. A speech synthesis apparatus according to claim 3, wherein the calculating means calculates the maximum value and a minimum value of the pitch contour from a creation time and a magnitude of the phrase command and a start time, an end time and a magnitude of the accent command, and

the modifying means modifies the magnitude of the phrase component and the magnitude of the accent component in such a manner that a difference between the maximum value and the minimum value is made substantially the same as an intonation value set by a user.