Methods for controlling the generation of speech from text representing one or more names

• US 5,832,435 A
• Filed: 01/29/1997
• Issued: 11/03/1998
• Est. Priority Date: 03/19/1993
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: NYNEX Science & Technology, Inc. (Verizon Communications Inc.)
• Inventors: Silverman, Kim Ernest Alexander
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Storm, Donald L.
• Application Number:
  US08/790,578
• Time in Patent Office: 643 Days
• Field of Search: 704/200, 704/260, 704/258, 704/235, 704/9, 704/266, 704/277
• 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
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

Improved automated synthesis of human audible speech from text is disclosed. Performance enhancement of the underlying text comprehensibility is obtained through prosodic treatment of the synthesized material, improved speaking rate treatment, and improved methods of spelling words or terms for the system user. Prosodic shaping of text sequences appropriate for the discourse in large groupings of text segments, with prosodic boundaries developed to indicate conceptual units within the text groupings, is implemented in a preferred embodiment.

Claims

1. A method of generating speech from a text segment including at least one name, the method comprising the steps of:

analyzing the beginning of the text segment to identify any prefixed title included in the text segment;

reducing the prosodic salience of any identified prefixed titles;

inserting a pause between any identified prefixed title and following text included in the text segment; and

operating a speech synthesizer to generate speech from the text segment, the generated speech reflecting the reduced prosodic salience of any identified prefixed title and any inserted pause.

2. A method of generating speech from a text segment, the method comprising the steps of:

analyzing the beginning of the text segment to identify any prefixed title included in the text segment;

reducing the prosodic salience of any identified prefixed titles;

inserting a pause between any identified prefixed title and following text included in the text segment;

analyzing the text segment to identify any separable accentable suffixes included in the text segment;

introducing a pause before any identified separable accentable suffice;

emphasizing any identified separable accentable suffice; and

operating a speech synthesizer to generate speech from the text segment, the generated speech reflecting the reduced prosodic salience of any identified prefixed title and any inserted pause.

3. The method of claim 2, wherein step of identifying prefixed titles includes the use of a table of prefixed titles, the table including Mr, Dr, Reverend and Captain.

4. The method of claim 3, wherein the step of identifying separable accentable suffixes includes the step of identifying suffixes including:

incorporated, junior, senior, II, and III.

5. The method of claim 2, further comprising the steps of:

analyzing the text segment to identify any deaccentable suffixes included in the text segment, a deaccentable suffice being a word which, when occurring after another word, joins the preceding word to make a single conceptual unit; and

reducing the salience of any identified deaccentable suffix.

6. The method of claim 5, further comprising the steps of:

storing a table of deaccentable suffixes; and

using the table of deaccentable suffixes when analyzing the text segment to identify any deaccentable suffixes included in the text segment.

7. The method of claim 6, wherein the table of deaccentable suffixes includes the words:

company, center, supply, limited, and corporation.

8. The method of claim 2, further comprising the steps of:

analyzing the text segment to identify any deaccentable suffixes included in the text segment, a deaccentable suffice being a word which, when occurring after another word, joins the preceding word to make a single conceptual unit;

for each identified deaccentable suffix, determining if the identified deaccentable suffix is preceded by additional text included in the text segment; and

for each identified deaccentable suffix for which it is determined that there is additional preceeding text, reducing the salience of said identified deaccentable suffix.

9. The method of claim 8, further comprising the step of:

checking to determine if a word is repeated in the text segment; and

if it is determined that a word is repeated, deaccenting the subsequent occurrence of the word.

10. The method of claim 9, further comprising the step of:

inserting, before an initial included in the text segment, an announcement of the initial'"'"'s letter status.

11. The method of claim 10, wherein the inserted announcement is one of the following phrases:

"the letter" and "initial".

12. The method of claim 8, further comprising the step of:

checking to determine if a word is repeated in the text segment and to determine if there is any text located between a first occurrence of a repeated word and a subsequent occurrence of the repeated word; and

upon determining that a word is repeated, and that there is text located between the first and second occurrences of the repeated word, deaccenting the subsequent occurrence of the word.

13. The method of claim 2, further comprising the step of:

inserting, before an initial included in the text segment, an announcement of the initial'"'"'s letter status, if it is determined through the use of a look-up table that said initial might be confused with a like sounding name.

14. The method of claim 2, further comprising the step of:

checking to determine if a word is repeated in the text segment; and

if it is determined that a word is repeated, deaccenting the subsequent occurrence of the word.

15. A method of generating speech from a text segment including a plurality of words and an initial, the method comprising the steps of:

inserting, before the initial included in the text segment, an announcement of the initial'"'"'s letter status, if it is determined through the use of a look-up table that said initial might be confused with a like sounding name; and

operating a speech synthesizer to generate speech from the text segment and the inserted announcement.

16. A method of generating speech from a text segment including a plurality of words and an initial, the method comprising the steps of:

inserting, before the initial included in the text segment, an announcement of the initial'"'"'s letter status; and

operating a speech synthesizer to generate speech from the text segment and the inserted announcement.

17. The method of claim 16, further comprising;

analyzing the beginning of the text segment to identify any prefixed title included in the text segment;

reducing the prosodic salience of any identified prefixed titles;

inserting a pause between any identified prefixed title and following text included in the text segment; and

operating a speech synthesizer to generate speech from the text segment, the generated speech reflecting the reduced prosodic salience of any identified prefixed title and any inserted pause.

18. A method of generating speech from a text segment including a plurality of words, the method comprising the steps of:

analyzing the beginning of the text segment to identify any prefixed title included in the text segment;

reducing the prosodic salience of any identified prefixed titles;

analyzing the text segment to identify any separable accentable suffixes included in the text segment;

introducing a pause before any identified separable accentable suffice;

emphasizing any identified separable accentable suffice; and

operating a speech synthesizer to generate speech from the text segment, the generated speech reflecting the reduced prosodic salience of any identified prefixed title and the emphasizing of any identified separable accentable suffice.

19. The method of claim 18, further comprising the steps of:

analyzing the text segment to identify any deaccentable suffixes included in the text segment, a deaccentable suffice being a word which, when occurring after another word, joins the preceding word to make a single conceptual unit; and

reducing the salience of any identified deaccentable suffix.

20. The method of claim 19, further comprising the steps of:

storing a table of deaccentable suffixes, the table including the words company, limited, and corporation; and

using the table of deaccentable suffixes when analyzing the text segment to identify any deaccentable suffixes included in the text segment.

21. The method of claim 18, further comprising the steps of:

analyzing the text segment to identify any deaccentable suffixes included in the text segment, a deaccentable suffice being a word which, when occurring after another word, joins the preceding word to make a single conceptual unit;

for each identified deaccentable suffix, determining if the identified deaccentable suffix is preceded by additional text included in the text segment; and

for each identified deaccentable suffix for which it is determined that there is additional preceeding text, reducing the salience of said identified deaccentable suffix.

22. A method of generating speech from a text segment including a prefixed title followed by words, the title and words representing a name, the method comprising the steps of:

analyzing the beginning of the text segment to identify any prefixed title included in the text segment;

controlling the prosodic salience of any identified prefixed title to be lower than the words in the text segment following the prefixed title;

inserting a pause between any identified prefixed title and following text included in the text segment; and

operating a speech synthesizer to generate speech from the text segment, the generated speech reflecting the controlled prosodic salience of any identified prefixed title and any inserted pause.