Multi-layered speech recognition apparatus and method

• US 8,380,517 B2
• Filed: 05/23/2012
• Issued: 02/19/2013
• 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:
  US13/478,656
• Publication Number:
  US 20120232893A1
• Time in Patent Office: 272 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: 704/270.1
• 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 speech recognition apparatus comprising:

a client capable of interacting with a server connected to the client via a network, wherein the client recognizes the speech continuously and sequentially in a multi-layered manner, optimally distributing a work load of the speech recognition in the client and in the server and improving the speech recognition,

wherein the client extracts characteristics of speech to be recognized, checks whether the client recognizes the speech using the extracted characteristic of the speech and recognizes the speech when the client can recognize the speech and transmits the the characteristic of the speech to the server when the client cannot recognize the speech, according to the checked result.

2. A speech recognition apparatus comprising:

a plurality of servers capable of interacting with a client connected to the servers via a network, wherein the servers comprise a first server, and a second server and are configured to recognize speech that is transmitted from the client continuously and sequentially in a multi-layered manner, optimally distributing a work load of the speech recognition in the client and in the servers,

wherein the first server checks whether the first server recognizes the speech transmitted from the client using a received characteristic of the speech, and recognizes the speech when the first server can recognize the speech and transmits the characteristic of the speech to the second server when the first server cannot recognize the speech according to the checked result, and

wherein the second server has a larger capacity of resource than the first server.