Hybrid speech recognition

• US 7,933,777 B2
• Filed: 08/30/2009
• Issued: 04/26/2011
• Est. Priority Date: 08/29/2008
• Status: Active Grant

• Current Assignee: Solventum Intellectual Properties Company (Solventum Corp.)
• Original Assignee: Multimodal Technologies Incorporated (3M Company)
• Inventors: Koll, Detlef
• Primary Examiner(s): Chawan; Vijay B
• Application Number:
  US12/550,380
• Publication Number:
  US 20100057450A1
• Time in Patent Office: 604 Days
• Field of Search: 704/270.1, 704/275, 704/270, 704/231, 704/251, 704/276, 704/257, 704/244, 704/9, 704/201, 370/353, 370/448, 370/458, 379/88.05, 379/88.01
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

A hybrid speech recognition system uses a client-side speech recognition engine and a server-side speech recognition engine to produce speech recognition results for the same speech. An arbitration engine produces speech recognition output based on one or both of the client-side and server-side speech recognition results.

Claims

1. A computer-implemented method performed by a client device, the method comprising:

(A) receiving a request from a requester to apply automatic speech recognition to an audio signal;

(B) providing the audio signal to a first automatic speech recognition engine in the client device;

(C) receiving first speech recognition results from the first automatic speech recognition engine at a first time;

(D) providing the audio signal to a second automatic speech recognition engine in a server device;

(E) determining whether second speech recognition results have been received by the client device from the second automatic speech recognition engine within a predetermined time period after the first time;

(F) if the second speech recognition results have been received by the client device within the predetermined time period, then providing the second speech recognition results to the requester in response to the request; and

(G) if the second speech recognition results have not been received by the client device within the predetermined time period, then providing the first speech recognition results to the requester in response to the request.

2. The method of claim 1, wherein (E) comprises selecting the predetermined time period based on a type of the second speech recognition results.

3. An apparatus comprising:

means for receiving a request from a requester to apply automatic speech recognition to an audio signal;

means for providing the audio signal to a first automatic speech recognition engine in the client device;

means for receiving first speech recognition results from the first automatic speech recognition engine at a first time;

means for providing the audio signal to a second automatic speech recognition engine in a server device;

means for determining whether second speech recognition results have been received by the client device from the second automatic speech recognition engine within a predetermined time period after the first time;

means for providing the second speech recognition results to the requester in response to the request if the second speech recognition results have been received by the client device within the predetermined time period; and

means for providing the first speech recognition results to the requester in response to the request if the second speech recognition results have not been received by the client device within the predetermined time period.