Abstract
Hybrid models of speech recognition combine a neural acoustic model with a language model, which rescores the output of the acoustic model to find the most linguistically likely transcript. Consequently the language model is of key importance in both open and domain specific speech recognition and much work has been done in adapting the language model to the speech input. We present an efficient pipeline for hybrid speech recognition where a domain-specific language model is selected for each utterance based on the result of domain classification. Experiments on public speech recognition datasets in the Vietnamese language show improvements in accuracy over the baseline speech recognition model for little increase in running time.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dehak N, Kenny PJ, Dehak R, Dumouchel P, Ouellet P (2011) Front-end factor analysis for speaker verification. IEEE Trans Audio Speech Lang Process 19:788–798
Echeverry-Correa J, Ferreiros-López J, Coucheiro-Limeres A, Córdoba R, Montero J (2015) Topic identification techniques applied to dynamic language model adaptation for automatic speech recognition. Expert Syst Appl 42(1):101–112
Haeb-Umbach R, Ney H (1992) Linear discriminant analysis for improved large vocabulary continuous speech recognition. In: Proceedings of ICASSP-92: 1992 IEEE international conference on acoustics, speech, and signal processing, vol 1, pp 13–16. https://doi.org/10.1109/ICASSP.1992.225984
Herms R, Richter D, Eibl M, Ritter M (2015) Unsupervised language model adaptation using utterance-based web search for clinical speech recognition. In: CLEF
Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of EMNLP. ACL, Doha, pp 1746–1751
Le-Hong P, Nguyen TMH, Nguyen TL, Ha ML (2015) Fast dependency parsing using distributed word representations. In: Trends and applications in knowledge discovery and data mining, Lecture Notes in Artificial Intelligence, vol 9441. Springer, Heidelberg
Liu Y, Liu F (2008) Unsupervised language model adaptation via topic modeling based on named entity hypotheses. In: International conference on acoustics, speech and signal processing. IEEE, Las Vegas
Ljolje A, Pereira F, Riley M (1999) Efficient general lattice generation and rescoring. In: EUROSPEECH
Nanjo H, Kawahara T (2003) Unsupervised language model adaptation for lecture speech recognition
Nguyen VH, Luong CM, Vu TT (2015) Tonal phoneme based model for Vietnamese LVCSR. In: 2015 International conference oriental COCOSDA held jointly with 2015 conference on Asian spoken language research and evaluation (O-COCOSDA/CASLRE), pp 118–122
Peddinti V, Povey D, Khudanpur S (2015) A time delay neural network architecture for efficient modeling of long temporal contexts. In: INTERSPEECH
Povey D, Ghoshal A, Boulianne G, Burget L, Glembek O, Goel N, Hannemann M, Motlicek P, Qian Y, Schwarz P, Silovsky J, Stemmer G, Vesely K: The Kaldi speech recognition toolkit. In: IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society, IEEE Catalog No.: CFP11SRW-USB
Stolcke A (2002) SRILM – an extensible language modeling toolkit. In: Proceedings of the 7th international conference on spoken language processing, pp 901–904
VLSP: VLSP 2018 - automatic speech recognition. http://www.vlsp.org.vn/vlsp2018/eval/asr (2018). Accessed 19 Aug 2018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Vu, D.H., Nguyen, V.H., Le-Hong, P. (2020). Online Adaptation of Language Models for Speech Recognition. In: Burduk, R., Kurzynski, M., Wozniak, M. (eds) Progress in Computer Recognition Systems. CORES 2019. Advances in Intelligent Systems and Computing, vol 977. Springer, Cham. https://doi.org/10.1007/978-3-030-19738-4_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-19738-4_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19737-7
Online ISBN: 978-3-030-19738-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)