Conference call service with speech processing for heavily accented speakers

• US 8,849,666 B2
• Filed: 02/23/2012
• Issued: 09/30/2014
• Est. Priority Date: 02/23/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Jaiswal, Peeyush, Vialpando, Burt Leo, Wang, Fang
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/403,470
• Publication Number:
  US 20130226576A1
• Time in Patent Office: 950 Days
• Field of Search: 704231-277
• US Class Current: 704/254
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing
• CPC Class Codes: G10L 21/003 Changing voice quality, e.g. pitch or formants

Abstract

Speech recognition processing captures phonemes of words in a spoken speech string and retrieves text of words corresponding to particular combinations of phonemes from a phoneme dictionary. A text-to-speech synthesizer then can produce and substitute a synthesized pronunciation of that word in the speech string. If the speech recognition processing fails to recognize a particular combination of phonemes of a word, as spoken, as may occur when a word is spoken with an accent or when the speaker has a speech impediment, the speaker is prompted to clarify the word by entry, as text, from a keyboard or the like for storage in the phoneme dictionary such that a synthesized pronunciation of the word can be played out when the initially unrecognized spoken word is again encountered in a speech string to improve intelligibility, particularly for conference calls.

Claims

1. A method of voice communication including voice recognition processing, said method comprising steps of

capturing and identifying phonemes of individual words of a spoken speech string comprising spoken words,

initiating a conference call,

interrupting said conference call when a word of said speech string is not recognized,

accessing text corresponding to a combination of phonemes identified in a spoken word of said speech string,

synthesizing a pronunciation of said word of said speech string to provide a synthesized pronunciation, and

substituting said synthesized pronunciation for said spoken word in said speech string.

2. The method as recited in claim 1, wherein said synthesized pronunciation is synthesized from said text.

3. The method as recited in claim 2, including a further step of displaying said text to a receiver of said voice communication.

4. The method as recited in claim 1, including a further step of displaying said text to a receiver of said voice communication.

5. The method a recited in claim 1, including further steps of

prompting a speaker of said speech string to enter a word of said speech string as text, and

storing said text of said word of said speech string to be accessed in accordance with said combination of phonemes.

6. The method as recited in claim 5, wherein said text of said word of said speech string is entered from a keyboard.

7. A method of providing a conference call service, said method comprising steps of

providing a phoneme dictionary storing text of words corresponding to combinations of spoken phonemes during a conference call,

initiating a conference call,

interrupting said conference call when a word of said speech string is not recognized,

accessing text corresponding to a combination of phonemes in a spoken word of said speech string,

synthesizing a pronunciation of said word of said speech string to provide a synthesized pronunciation, and

substituting said synthesized pronunciation for said spoken word in said speech string.

8. The method as recited in claim 7, including the further step of

providing said text corresponding to a spoken word to participants in said conference call.

9. The method as recited in claim 8, including the further step of

prompting a speaker of said speech string to enter text of a word of said speech string.

10. The method as recited in claim 9, wherein said text is entered from a keyboard in response to said prompt.

11. The method as recited in claim 9, wherein said prompting step is performed responsive to a participant in said conference call.

12. Data processing apparatus configured to provide

a connection to a communication system capable of conducting a conference call,

recognition of combinations of phonemes comprising words of a spoken speech string,

interruption of said conference call when a word of said speech string is not recognized,

memory comprising a phoneme dictionary containing text of words corresponding to respective ones of said combinations of phonemes, and

a text-to-speech synthesizer for synthesizing words corresponding to said combinations of phonemes.

13. Data processing apparatus as recited in claim 12, further comprising

a display for prompting a speaker to provide text corresponding to a word of said speech string for storage in said memory with a combination of phonemes comprising said word of said speech string.

14. Data processing apparatus as recited in claim 13, further comprising

a communication arrangement to transmit said speech string having a word synthesized by said text-to-speech synthesizer substituted for a word of said speech string as spoken by a speaker.

15. Data processing apparatus as recited in claim 14 wherein said communication arrangement also transmits said text of said word substituted in said speech string.

16. Data processing apparatus as recited in claim 13, further comprising

conference call control processing.