DocumentCode :
2660372
Title :
Word-lattice based spoken-document indexing with standard text indexers
Author :
Seide, Frank ; Thambiratnam, Kit ; Yu, Roger Peng
Author_Institution :
Microsoft Res. Asia, Beijing Sigma Center, Beijing
fYear :
2008
fDate :
15-19 Dec. 2008
Firstpage :
293
Lastpage :
296
Abstract :
Indexing the spoken content of audio recordings requires automatic speech recognition, which is as of today not reliable. Unlike indexing text, we cannot reliably know from a speech recognizer whether a word is present at a given point in the audio; we can only obtain a probability for it. Correct use of these probabilities significantly improves spoken-document search accuracy. In this paper, we will first describe how to improve accuracy for "web-search style" (AND/phrase) queries into audio, by utilizing speech recognition alternates and word posterior probabilities based on word lattices. Then, we will present an end-to-end approach to doing so using standard text indexers, which by design cannot handle probabilities and unaligned alternates. We present a sequence of approximations that transform the numeric lattice-matching problem into a symbolic text-based one that can be implemented by a commercial full-text indexer. Experiments on a 170-hour lecture set show an accuracy improvement by 30-60% for phrase searches and by 130% for two-term AND queries, compared to indexing linear text.
Keywords :
audio recording; indexing; speech recognition; audio indexing; queries; speech recognition; spoken-document indexing; text indexers; word posterior probabilities; word-lattice; Asia; Audio recording; Automatic speech recognition; Indexing; Lattices; Search engines; Speech recognition; Text recognition; Video recording; Vocabulary; Audio Indexing; Full-Text Indexing; Posterior; Word Lattice;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Spoken Language Technology Workshop, 2008. SLT 2008. IEEE
Conference_Location :
Goa
Print_ISBN :
978-1-4244-3471-8
Electronic_ISBN :
978-1-4244-3472-5
Type :
conf
DOI :
10.1109/SLT.2008.4777898
Filename :
4777898
Link To Document :
بازگشت