Learning sub-word units for open vocabulary speech recognition

Authors:
Carolina Parada;Mark Dredze;Abhinav Sethy;Ariya Rastrow
Affiliations:
Johns Hopkins University, Baltimore, MD;Johns Hopkins University, Baltimore, MD;IBM T. J. Watson Research Center, Yorktown Heights, NY;Johns Hopkins University, Baltimore, MD
Venue:
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Year:
2011

Citing 8
Cited 0

Modelling out-of-vocabulary words for robust speech recognition

Modelling out-of-vocabulary words for robust speech recognition
Vocabulary independent spoken term detection

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
A new method for OOV detection using hybrid word/fragment system

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Effect of pronounciations on OOV queries in spoken term detection

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Unsupervised morphological segmentation with log-linear models

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Analysis and processing of lecture audio data: preliminary investigations

SpeechIR '04 Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004
Linguistically-motivated sub-word modeling with applications to speech recognition

Linguistically-motivated sub-word modeling with applications to speech recognition
Contextual information improves OOV detection in speech

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems; new words can then be represented by combinations of sub-word units. Previous work heuristically created the sub-word lexicon from phonetic representations of text using simple statistics to select common phone sequences. We propose a probabilistic model to learn the subword lexicon optimized for a given task. We consider the task of out of vocabulary (OOV) word detection, which relies on output from a hybrid model. A hybrid model with our learned sub-word lexicon reduces error by 6.3% and 7.6% (absolute) at a 5% false alarm rate on an English Broadcast News and MIT Lectures task respectively.