Method and device for rating of speech quality by calculating time delays from onset of vowel sounds

• US 5,806,028 A
• Filed: 02/14/1996
• Issued: 09/08/1998
• Est. Priority Date: 02/14/1995
• Status: Expired due to Term

• Current Assignee: Intellectual Ventures I LLC (Intellectual Ventures LLC)
• Original Assignee: Telia AB (Government of Norway)
• Inventors: Lyberg, Bertil
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): COLLINS, ALPHONSO
• Application Number:
  US08/601,508
• Time in Patent Office: 937 Days
• Field of Search: 395/2.79, 395/2.86, 704/231, 704/237-240, 704/246, 704/248, 704/235
• US Class Current: 704/231
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management

Abstract

A method and device for determining quality of speech. The speech to be evaluated is listened to by a person who reproduces the speech. The end of vowel sounds in the produced and reproduced speech respectively are determined. The difference between the ends of the vowel sounds is registered. From the obtained time differences an average value is determined. The average value indicates the quality of the produced speech. The invention can be used for evaluation of different speech sources.

Claims

1. A method for determining speech quality, comprising the steps of:

providing a first speech;

providing a second speech, wherein said second speech is a reproduction of said first speech; and

determining time differences between corresponding starts of each vowel sound of each word in said first and second speech, wherein said time differences are a measure of a match of said first speech and said second speech and providing an output of said time differences.

2. A method as set forth in claim 1, wherein said step of providing a second speech comprises a person listening to and repeating said first speech.

3. A method as set forth in claim 1, wherein said step of providing a first speech comprises providing said first speech from a source selected from the group consisting of a text-to-speech converter, a person reading a text associated with said first speech, and an audio play-back device.

4. A method as set forth in claim 2, wherein

said step of providing a first speech comprises providing a first speech of a known quality;

and

said step of determining the time differences comprises indicating a calibration associated with said first speech.

5. A method set forth in claim 1, further comprising the step of determining an average value of said time differences, wherein said average value indicates said measure of a match of said first speech and said second speech.

6. A method as set forth in claim 2, further comprising the step of categorizing said first speech according to a category of said person.

7. An apparatus for determining speech quality, comprising:

means for converting a first speech to a first electrical signal;

means for converting a second speech to a second electrical signal; and

means for determining time differences between corresponding starts of each vowel sound of each word in said first speech and second speech based upon first and second electrical signals, wherein said time differences indicate a measure of a match of said first speech and said second speech and means for outputting said time differences.

8. An apparatus as set forth in claim 7, further comprising a source for producing said first speech, wherein said source is selected from the group consisting of a text-to-speech converter and audio play-back device.

9. An apparatus as set forth in claim 7, further comprising means for determining an average value of said first time differences, wherein said average value indicates said measure of a match of said first speech and said second speech.