Method of an arrangement for speech recognition with speech velocity adaptation

• US 6,629,072 B1
• Filed: 08/28/2000
• Issued: 09/30/2003
• Est. Priority Date: 08/30/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications Austria Gmbh (Microsoft Corporation)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Thelen, Eric, Wutte, Heribert
• Primary Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US09/649,675
• Time in Patent Office: 1,128 Days
• Field of Search: 704/251, 704/275
• US Class Current: 704/251
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 2015/221 Announcement of recognition results

Abstract

With a method of and an arrangement for speech recognition a measurement of the speech velocity rate is carried out in a measuring unit (2) so as to reduce the error rate of the recognition result, which speech velocity is announced to the speaker via an output unit (3) and warning is given if the velocity is out of speech recognition adaptation range.

Claims

1. A method of speech recognition characterized in that

a speech velocity is measured which is announced to the speaker.

2. A method as claimed in claim 1, characterized in that

the measured speech velocity is fed to the speech recognizer (1).

3. A method as claimed in claim 1, characterized in that

the speech velocity is determined by means of a measuring unit (2) during the recognition and/or training.

4. A method as claimed in claim 1, characterized in that

recognized phonemes and/or words are measured per predefinable time interval.

5. A method as claimed in claim 1, characterized in that

the speech velocity is shown as a function of a threshold value.

6. A method as claimed in claim 5, characterized in that

the threshold value is determined as a function of the error rate.

7. A method as claimed in claim 1, characterized in that

the speech velocity is continuously shown to the user.

8. The method as claimed in claim 1, wherein the providing step includes informing the speaker of the speech velocity.

9. A speech recognition device, characterized in that

a measuring unit (2) determines a speech velocity, determines whether, based on the measured speech velocity, speech recognition adaptation can be made, and informs the speaker thereof by means of an output unit (3).

10. A device as claimed in claim 9, characterized in that

the output unit (3) shows a range of the speech velocity by means of colors.

11. A device as claimed in claim 9, characterized in that

a transgression of the speech velocity is indicated by means of an audio output.