Multistage utterance verification for keyword recognition-based online spoken content retrieval
- 27 September 2012
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 58 (3), 1000-1005
- https://doi.org/10.1109/TCE.2012.6311348
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.Keywords
This publication has 10 references indexed in Scilit:
- Performance Analysis and Improvement of Turkish Broadcast News RetrievalIEEE Transactions on Audio, Speech, and Language Processing, 2011
- GMM adaptation based online speaker segmentation for spoken document retrievalIEEE Transactions on Consumer Electronics, 2010
- A Supervised Framework for Keyword Extraction From Meeting TranscriptsIEEE Transactions on Audio, Speech, and Language Processing, 2010
- The design of a speech interactivity embedded module and its applications for mobile consumer devicesIEEE Transactions on Consumer Electronics, 2008
- Retrieval and browsing of spoken contentIEEE Signal Processing Magazine, 2008
- Study of the Design and Implementation of Speech Keyword Recognition System based on Streaming MediaPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Confidence measures for speech recognition: A surveySpeech Communication, 2005
- Phoneme Based Acoustics Keyword Spotting in Informal Continuous SpeechLecture Notes in Computer Science, 2005
- The LIMSI Broadcast News transcription systemSpeech Communication, 2002
- Phonetic Searching vs. LVCSR: How to Find What You Really Want in Audio ArchivesInternational Journal of Speech Technology, 2002