System and method for latency reduction for automatic speech recognition using partial multi-pass results

• US 8,010,360 B2
• Filed: 12/15/2009
• Issued: 08/30/2011
• Est. Priority Date: 12/23/2003
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Bacchiani, Michiel Adriaan Unico, Amento, Brian Scott
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US12/638,604
• Publication Number:
  US 20100094628A1
• Time in Patent Office: 623 Days
• Field of Search: 704/231, 704/235, 704/244, 704/239, 704/240, 704/251, 704/255, 704/270, 704/252, 704/276, 704/246, 704/257
• US Class Current: 704/252
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

A system and method is provided for reducing latency for automatic speech recognition. In one embodiment, intermediate results produced by multiple search passes are used to update a display of transcribed text.

Claims

1. A method for reducing latency in automatic speech recognition, the method comprising:

transcribing speech data using a first automatic speech recognition pass, which operates at a first transcription rate near real time, to produce first transcription data;

displaying the first transcription data on a display unit;

determining, via a processor of a computing device, how many additional automatic speech recognition transcription passes are needed, wherein the additional automatic speech recognition transcription passes are slower and more accurate than the first automatic speech recognition pass, to produce at least a second transcription data; and

displaying an indication of how many additional automatic speech recognition transcription passes are forthcoming that will update the first transcription data displayed on the display unit.

2. The method of claim 1, wherein the first automatic speech recognition pass operates at real time.

3. The method of claim 1, wherein the first automatic speech recognition pass operates at greater than real time.

4. The method of claim 1, wherein displaying the first transcription data further comprises displaying an indicator that signifies that more accurate transcription data is being generated.

5. The method of claim 1, wherein the first transcription data is displayed in at least one of a different color and a different shade as compared to the indication.

6. The method of claim 1, wherein portions of the first transcription data having a relatively lower confidence score are distinctly displayed as compared to other portions of the first transcription data having a relatively higher confidence score.

7. The method of claim 6, wherein the portions of the first transcription data having the relatively lower confidence score are displayed in a darker shade as compared to the other portions of the first transcription data having the relatively higher confidence score.

8. The method of claim 6, wherein the portions of the first transcription data having the relatively lower confidence score enable a user to listen to corresponding portions of the speech data.

9. The method of claim 1, wherein the additional automatic speech recognition transcription passes of the speech data are normalized automatic speech recognition passes.