System and method for converting text-to-voice

• US 6,871,178 B2
• Filed: 03/27/2001
• Issued: 03/22/2005
• Est. Priority Date: 10/19/2000
• Status: Active Grant

• Current Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Original Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Inventors: Case, Eliot M., Weirauch, Judith L.
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/818,968
• Publication Number:
  US 20020103648A1
• Time in Patent Office: 1,456 Days
• Field of Search: 704/208, 704/209, 704/214, 704/258, 704/260
• US Class Current: 704/260
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• 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

Abstract

A method for converting text to concatenated voice by utilizing a digital voice library and a set of playback rules is provided. The digital voice library includes a plurality of speech items and a corresponding plurality of voice recordings. Each speech item corresponds to at least one available voice recording. Multiple voice recordings that correspond to a single speech item represent various inflections of that single speech item. The method includes receiving text data, converting the text data into a sequence of speech items in accordance with the digital voice library. The method further includes establishing multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, that represent various ligatures for the single inflection of the single speech item with adjacent speech items.

Claims

1. A method for converting text to concatenated voice by utilizing a digital voice library and a set of playback rules, the digital voice library including a plurality of speech items and a corresponding plurality of voice recordings wherein each speech item corresponds to at least one available voice recording wherein multiple voice recordings that correspond to a single speech item represent various inflections of that single speech item, the method including receiving text data, converting the text data into a sequence of speech items in accordance with the digital voice library, the method further comprising:

establishing multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, that represent various ligatures for the single inflection of the single speech item with adjacent speech items wherein the recordings for a single inflection of a single speech item are a limited set of recordings that represent a limited set of ligatures with adjacent speech items including only recordings having a vowel at either end and recordings having no surrounding ligature distortions.

2. The method of claim 1 wherein the multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, represent various ending ligatures for ending phonemes of the single inflection of the single speech item with beginning phonemes of adjacent speech items.

3. The method of claim 1 wherein the multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, represent various beginning ligatures for beginning phonemes of the single inflection of the single speech item with ending phonemes of adjacent speech items.

4. The method of claim 1 wherein the multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, represent various beginning and ending ligatures for beginning and ending phonemes of the single inflection of the single speech item with ending and beginning phonemes of adjacent speech items.

5. The method of claim 4 wherein the ligatures include ligatures associated with vowel staging.

6. The method of claim 5 wherein the ligatures include ligatures associated with vowel staging, consonant staging, and fricative consonant staging.

7. The method of claim 1 wherein the ligatures include ligatures associated with vowel staging.

8. The method of claim 7 wherein the ligatures include ligatures associated with vowel staging, consonant staging, and fricative consonant staging.

9. A method for converting text to concatenated voice by utilizing a digital voice library and a set of playback rules, the digital voice library including a plurality of speech items and a corresponding plurality of voice recordings wherein each speech item corresponds to at least one available voice recording wherein multiple voice recordings that correspond to a single speech item represent various inflections of that single speech item, the method including receiving text data, converting the text data into a sequence of speech items in accordance with the digital voice library, the method further comprising:

establishing multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, that represent various ligatures for the single inflection of the single speech item with adjacent speech items wherein the recordings for a single inflection of a single speech item are a limited set of recordings that represent a limited set of ligatures with adjacent speech items including only recordings having a vowel at either end and recordings having no surrounding ligature distortions;

determining a desired inflection for each speech item in the sequence of speech items based on the set of playback rules;

determining a sequence of voice recordings by determining a voice recording for each speech item based on the desired inflection for the particular speech item, the available voice recordings that correspond to the particular speech item, and the ligatures for the particular speech item with adjacent speech items; and

generating voice data based on the sequence of voice recordings by concatenating adjacent recordings in the sequence of voice recordings.

10. The method of claim 9 wherein the multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, represent various ending ligatures for ending phonemes of the single inflection of the single speech item with beginning phonemes of adjacent speech items, and

wherein determining the sequence of voice recordings by determining a voice recording for each speech item is further based on ending ligatures for ending phonemes of the particular speech item with beginning phonemes of adjacent speech items.

11. The method of claim 9 wherein the multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, represent various beginning ligatures for beginning phonemes of the single inflection of the single speech item with ending phonemes of adjacent speech items, and

wherein determining the sequence of voice recordings by determining a voice recording for each speech item is further based on beginning ligatures for beginning phonemes of the particular speech item with ending phonemes of adjacent speech items.

12. The method of claim 9 wherein the multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, represent various beginning and ending ligatures for beginning and ending phonemes of the single inflection of the single speech item with ending and beginning phonemes of adjacent speech items, and

wherein determining the sequence of voice recordings by determining a voice recording for each speech item is further based on beginning and ending ligatures for beginning and ending phonemes of the particular speech item with ending and beginning phonemes of adjacent speech items.

13. The method of claim 12 wherein the ligatures include ligatures associated with vowel staging.

14. The method of claim 13 wherein the ligatures include ligatures associated with vowel staging, consonant staging, and fricative consonant staging.

15. The method of claim 9 wherein the ligatures include ligatures associated with vowel staging.

16. The method of claim 15 wherein the ligatures include ligatures associated with vowel staging, consonant staging, and fricative consonant staging.

17. A method for converting text to concatenated voice by utilizing a digital voice library and a set of playback rules, the digital voice library including a plurality of speech items and a corresponding plurality of voice recordings wherein each speech item corresponds to at least one available voice recording wherein multiple voice recordings that correspond to a single speech item represent various inflections of that single speech item, the method including receiving text data, convening the text data into a sequence of speech items in accordance with the digital voice library, the method further comprising:

establishing multiple voice recordings in the digital voice library that correspond to a single inflection of a single speech item, for a plurality of inflections of a plurality of speech items, that represent various ligatures for the single inflection of the single speech item with adjacent speech items wherein the recordings for a single inflection of a single speech item are a limited set of recordings that represent a limited set of ligatures with adjacent speech items including only recordings having a phoneme at either end from a limited set of phonetic groups and recordings having no surrounding ligature distortions.

18. The method of claim 17 wherein the limited set of phonetic groups includes plosives, fricatives, affricates, nasals, laterals, trills, glides, vowels, dipthongs and schwa.