Multistage Utterance Verification for Keyword Recognition-based Online Spoken Content Retrieval

Title
Multistage Utterance Verification for Keyword Recognition-based Online Spoken Content Retrieval
Author(s)
박정식Jang, Gil-Jin[Jang, Gil-Jin]Kim, Ji-Hwan[Kim, Ji-Hwan]
Keywords
SPEECH
Issue Date
201208
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, v.58, no.3, pp.1000 - 1005
Abstract
This paper proposes a multistage utterance verification method as a post-processing technique for online spoken content retrieval in portable electric devices. The online spoken content retrieval system analyzes spoken content in an online manner and searches speech segments of pre-defined keywords. To maintain stable performance, we propose a reliable post-processing technique that verifies whether a found utterance or a candidate keyword segment can ultimately be categorized as a keyword. The proposed method involves a two-stage procedure for utterance verification. The first stage utilizes a confidence measure based on N-best log-likelihood recognition results. In the second stage, Dynamic Time Warping (DTW) algorithm is applied to obtain a verification result. As neither of these procedures requires high computational time and intensity, both are very suitable to online retrieval in portable devices such as smartphones. To assess the proposed technique, experiments on multimedia content retrieval tasks were performed using spoken broadcast news data. The evaluation results revealed that the performance of the proposed method was superior to that of the conventional approach(1).
URI
http://hdl.handle.net/YU.REPOSITORY/27483
ISSN
0098-3063
Appears in Collections:
공과대학 > 모바일정보통신공학과 > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE