Multi-layered speech recognition apparatus and method

• US 8,892,425 B2
• Filed: 01/02/2013
• Issued: 11/18/2014
• Est. Priority Date: 10/08/2004
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lee, Jaewon, Cho, Jeongmi, Hwang, Kwangil, Lee, Yongbeom, Kim, Jeongsu
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US13/732,576
• Publication Number:
  US 20130124197A1
• Time in Patent Office: 685 Days
• Field of Search: 704/277, 704/270.1, 704/270, 704/257, 704/246, 704/235, 704/219, 704/2, 700/94, 455/444, 455/422.1, 382/239, 382/166, 375/340, 375/295, 370/204
• US Class Current: 704/201
• CPC Class Codes: G10L 15/08 Speech classification or search
• 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 multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2≦n≦N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n−1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

Claims

1. A method of speech recognition, the method comprising;

obtaining the speech from a user;

characterizing the speech in a client; and

optimally distributing a workload of the speech recognition in the client and one or more servers, by determining whether the speech recognition for the speech can be performed in the client, based on the characterizing of the speech.

2. The method of claim 1, wherein the distributing a workload of the speech recognition comprises transferring the workload of the speech recognition for the speech from the client to the one or more servers when it is determined that the speech recognition cannot be performed in the client and performing the speech recognition for the speech in the client when it is determined that the speech recognition can be performed in the client.

3. A method of speech recognition, the method comprising;

obtaining speech from a user;

characterizing speech in a client; and

optimally distributing a workload of the speech recognition in the client and servers, based on the characterizing of the speech,

wherein the distributing a workload of the speech recognition in the client and server is performed by the client and a first server, the distributing a workload of the speech recognition in servers is performed by a n-th server, and

wherein the first server has a larger capacity of resource than the client and the n-th server has a larger capacity of resource than the (n−

1)-th server.

4. A method of speech recognition using a client and a server, the method comprising;

extracting, in the client, a characteristic of speech to be recognized;

determining whether the client recognizes the speech based on the extracted characteristic of the speech; and

optimally distributing a workload of the speech recognition in the client and the server based on the determining.

5. The method of claim 4, wherein in the determining of whether the client recognizes the speech, the client recognizes the speech when the client determines that the client can recognize the speech and otherwise the client transmits the characteristic of the speech to be recognized to the server when the client cannot recognize the speech.