Apparatus and method for testing speech recognition in mobile environments

• US 20030236672A1
• Filed: 07/31/2002
• Published: 12/25/2003
• Est. Priority Date: 10/30/2001
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Lubensky, David M., Aaron, Andrew, Das, Subrata K.
• Granted Patent: US 7,487,084 B2
• Time in Patent Office: Days
• US Class Current: 704/277
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems

Abstract

A testing arrangement provided for speech recognition systems in vehicles. Preferably included are a “mobile client” secured in the vehicle and driven around at a desired speed, an audio system and speaker which plays back a set of prerecorded utterances stored digitally in a computer arrangement such that the speech of a human being is simulated, transmission of the speech signal to a server, followed by speech recognition and signal-to-noise ratio (SNR) computation. Here, the acceptability of the vehicular speech recognition system is preferably determined via comparison with pre-specified standards of recognition accuracy and SNR values.

Claims

1. An apparatus for testing speech recognition in a vehicle, said apparatus comprising:

a speaker arrangement which propagates speech output;

a testing arrangement adapted to test the accuracy of speech input associated with the speech output propagated by said speaker arrangement;

wherein said speaker arrangement is configured to simulate the propagation of a human voice.

2. The apparatus according to claim 1, wherein said speaker arrangement is configured to propagate speech output from a position corresponding to the mouth of an average-sized human seated in the vehicle.

3. The apparatus according to claim 2, wherein said speaker arrangement is dimensioned to be seated on a vehicle seat and to propagate speech output from a position corresponding to the mouth of an average-sized human seated in the vehicle.

4. The apparatus according to claim 3, wherein said speaker arrangement comprises a torso portion and a head portion, said torso portion being dimensioned substantially similmarly to an average human torso and said head portion being dimensioned substantially similarly to an average human head, wherein speech output propagates from said head portion from a position corresponding to a human mouth.

5. The apparatus according to claim 1, wherein said testing arrangement is integrable with a receiver arrangement adapted to pick up speech output from said speaker arrangement.

6. The apparatus according to claim 1, wherein said testing arrangement comprises a speech recognizer.

7. The apparatus according to claim 6, wherein said testing arrangement is further adapted to calculate a speech recognition score.

8. The apparatus according to claim 6, wherein said testing arrangement is further adapted to calculate a signal-to-noise ratio.

9. The apparatus according to claim 1, wherein said speaker arrangement is adapted to propagate prerecorded speech output.

10. A method of testing speech recognition in a vehicle, said apparatus comprising:

propagating speech output;

testing the accuracy of speech input associated with the speech output propagated by said speaker arrangement; and

wherein said propagating step comprises simulating the propagation of a human voice.

11. The method according to claim 10, wherein said simulating step comprises propagating speech output from a position corresponding to the mouth of an average-sized human seated in the vehicle.

12. The method according to claim 11, further comprising:

providing a speaker arrangement to perform said propagating step;

dimensioning said speaker arrangement to be seated on a vehicle seat and to propagate speech output from a position corresponding to the mouth of an average-sized human seated in the vehicle.

13. The method according to claim 12, wherein said step of providing a speaker arrangement comprises providing a torso portion and a head portion, said torso portion being dimensioned substantially similmarly to an average human torso and said head portion being dimensioned substantially similarly to an average human head, wherein speech output propagates from said head portion from a position corresponding to a human mouth.

14. The method according to claim 10, further comprising the steps of:

providing a testing arrangement to perform said testing step; and

integrating said testing arrangement with a receiving arrangement adapted to pick up propagated speech output.

15. The method according to claim 10, wherein said testing step comprises the step of performing speech recognition.

16. The method according to claim 15, wherein said testing step comprises calculating a speech recognition score.

17. The method according to claim 15, wherein said testing step comprises calculating a signal-to-noise ratio.

18. The method according to claim 10, wherein said propagating step comprises propagating prerecorded speech output.

19. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for testing speech recognition in a vehicle, said apparatus comprising:

propagating speech output;

testing the accuracy of speech input associated with the speech output propagated by said speaker arrangement; and

wherein said propagating step comprises simulating the propagation of a human voice.