Document level semantic context for retrieving OOV proper names
Authors:
- 1 March 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 6050-6054
Abstract
Recognition of Proper Names (PNs) in speech is important for content based indexing and browsing of audio-video data. However, many PNs are Out-Of-Vocabulary (OOV) words for LVCSR systems used in these applications due to the diachronic nature of data. By exploiting semantic context of the audio, relevant OOV PNs can be retrieved and then the target PNs can be recovered. To retrieve OOV PNs, we propose to represent their context with document level semantic vectors; and show that this approach is able to handle less frequent OOV PNs in the training data. We study different representations, including Random Projections, LSA, LDA, Skip-gram, CBOW and GloVe. A further evaluation of recovery of target OOV PNs using a phonetic search shows that document level semantic context is reliable for recovery of OOV PNs.Keywords
This publication has 14 references indexed in Scilit:
- OOV Proper Name retrieval using topic and lexical context models2015
- Combining local and broad topic context to improve term detection2014
- Glove: Global Vectors for Word Representation2014
- Person name recognition in ASR outputs using continuous context models2013
- An audio indexing system for election video material2009
- Introduction to Information Retrieval2008
- Open Vocabulary ASR for Audiovisual Document Indexation2006
- Improving out-of-vocabulary name resolutionComputer Speech & Language, 2005
- A guided tour to approximate string matchingACM Computing Surveys, 2001
- Tagging unknown proper names using decision trees2000