System and method for converting text-to-voice

• US 7,451,087 B2
• Filed: 03/27/2001
• Issued: 11/11/2008
• Est. Priority Date: 10/19/2000
• Status: Expired due to Term

• Current Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Original Assignee: Qwest Communications International Incorporated (Lumen Technologies, Inc.)
• Inventors: Case, Eliot M., Phillips, Richard P.
• Primary Examiner(s): Hudspeth; David R.
• Assistant Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US09/818,207
• Publication Number:
  US 20020077821A1
• Time in Patent Office: 2,786 Days
• Field of Search: 704/260, 704/258
• US Class Current: 704/267
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 13/07 Concatenation rules

Abstract

A method for converting text to concatenated voice by utilizing a digital voice library and a set of playback rules is provided. The method includes receiving and expanding text data to form a sequence of text and pseudo words. The sequence of text and pseudo words is converted into a sequence of speech items, and the sequence of speech items is converted into a sequence of voice recordings. The method includes generating voice data on the sequence of voice recordings by concatenating adjacent recordings in the sequence of voice recordings.

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, multiple voice recordings corresponding to a single speech item representing various inflections of that single speech item, the method 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;

receiving text data;

expanding the text data to form a sequence of text and pseudo words;

converting the sequence of text and pseudo words into a sequence of speech items in accordance with the digital voice library, wherein at least one speech item in the sequence of speech items corresponds to multiple voice recordings;

converting the sequence of speech items into a sequence of voice recordings in accordance with the set of playback rules, wherein selecting a voice recording where multiple voice recordings are available for a speech item is based on context around the speech item in the text data;

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

wherein the plurality of speech items includes a plurality of phrases, and wherein converting the sequences of text and pseudo words further includes parsing the sequence of text and pseudo words to determine any phrases.

2. The method of claim 1 wherein expanding the text data further comprises:

searching the text data for an abbreviation; and

expanding any abbreviation contained in the text data into at least one pseudo word.

3. The method of claim 1 wherein expanding the text data further comprises:

searching the text data for a numerical suffix; and

expanding any numerical suffix contained in the text data into at least one pseudo word.

4. The method of claim 1 wherein expanding the text data further comprises:

searching the text data for a telephone number; and

expanding any telephone number contained in the text data into at least one pseudo word.

5. The method of claim 1 wherein expanding the text data further comprises:

searching the text data for a number that includes a comma; and

expanding any number that includes a comma contained in the text data into at least one pseudo word.

6. The method of claim 1 wherein expanding the text data further comprises:

searching the text data for an Internet mail address; and

expanding any Internet mail address contained in the text data into at least one pseudo word.

7. The method of claim 1 wherein expanding the text data further comprises:

searching the text data for an Internet Universal Resource Locator; and

expanding any Internet Universal Resource Locator in the text data into at least one pseudo word.

8. The method of claim 1 wherein the plurality of speech items includes a plurality of words, and wherein converting the sequence of text and pseudo words further comprises:

parsing the sequence of text and pseudo words to determine any words.

9. The method of claim 8 wherein the plurality of speech items includes a plurality of syllables, and wherein converting the sequence of text and pseudo words further comprises:

parsing the sequence of text and pseudo words to determine any syllables.