Abstract
Previous approaches to spontaneous speech recognition address the multiple pronunciation problem by modeling the alteration of the pronunciation on a phoneme to phoneme level. However, the phonetic transformation effects induced by the pronunciation of the whole sentence are not considered yet. In this paper we attempt to model the sequence-based pronunciation variation using a noisy-channel approach where the spontaneous phoneme sequence is considered as a “noisy” string and the goal is to recover the “clean” string of the word sequence. Hereby, the whole word sequence and its effect on the alternation of the phonemes will be taken into consideration. Moreover, the system not only learns the phoneme transformation but also the mapping from the phoneme to the word directly. In this preliminary study, first the phonemes will be recognized with the present recognition system and afterwards the pronunciation variation model based on the noisy-channel approach will map from the phoneme to the word level. Our experiments use Switchboard as spontaneous speech corpus. The results show that the proposed method improves the word accuracy consistently over the conventional recognition system. The best system achieves up to 38.9% relative improvement to the baseline speech recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Al-Onaizan, Y., Papineni, K.: Distortion models for statistical machine translation. In: Proc. ACL/COLING, pp. 529–536 (2006)
Bates, A., Osterndorf, M., Wright, R.: Symbolic phonetic features for modeling of pronunciation variation. Speech Communication 49, 83–97 (2007)
Brown, P., Pietra, S., Pietra, V.: The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics 19(2), 263–311 (1993)
Chen, K., Hasegawa-Johnson, M.: Modeling pronunciation variation using artificial neural networks for English spontaneous speech. In: Proc. ICSLP, pp. 1461–1464 (2004)
Finch, A., Denoual, E., Okuma, H., Paul, M., Yamamoto, H., Yasuda, K., Zhang, R., Sumita, E.: The NICT/ATR speech translation system for IWSLT 2007. In: Proc. IWSLT, pp. 103–110 (2007)
Fosler-Lussier, E.: Contextual word and syllable pronunciation models. In: Proc. IEEE ASRU Workshop (1999)
Godfrey, J., Holliman, E., McDaniel, J.: SWITCHBOARD: Telephone speech corpus for research and development. In: Proc. ICSLP, pp. 24–27 (1996)
Jitsuhiro, T., Matsui, T., Nakamura, S.: Automatic generation of non-uniform HMM topologies based on the MDL criterion. IEICE Trans. Inf. Syst. E87-D (8) (2004)
King, S., Bartels, C., Bilmers, J.: Small vocabulary tasks from Switchboard 1. In: Proc. EUROSPEECH, pp. 3385–3388 (2005)
Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proc. the Human Language Technology Conference, pp. 127–133 (2003)
Livescu, K., Glass, J.: Feature-based pronunciation modeling for speech recognition. In: Proc. HLT/NAACL (2004)
Och, F., Ney, H.: Discriminative training and maximum entropy models for statistical machine translation. In: Proc. ACL, pp. 295–302 (2002)
Och, F., Ney, H.: A systematic comparison of various statistical alignment models. Computational Linguistics 29(1), 19–51 (2003)
Pallet, D.: A look at NISTS’s benchmark ASR tests: Past, present, future. In: Proc. ASRU, pp. 483–488 (2003)
Pallett, S., Fiscus, J., Fisher, M., Garofolo, J., Lund, B., Przybocki, M.: 1993 benchmark tests for the ARPA spoken language program. In: Proc. Spoken Language Technology Workshop (1994)
Paul, D.B., Baker, J.: The design for the Wall Street journal-based CSR corpus. In: Proc. ICSLP (1992)
Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., Zavaliagkos, G.: Stochastic pronunciation modelling from handlabelled phonetic corpora. In: Proc. ETRW on Modeling Pronunciation Variation for Automatic Speech Recognition, pp. 109–116 (1998)
Sakti, S., Markov, S., Nakamura, S.: Probabilistic pronunciation variation model based on Bayesian networks for conversational speech recognition. In: Second International Symposium on Universal Communication (2008)
Stolcke, A.: SRILM - an extensible language modeling toolkit. In: Proc. ICSLP, pp. 901–904 (2002)
Lo, W.K., Soong, F.K.: Generalized posterior probability for minimum error verification of recognized sentences. In: Proc. ICASSP, pp. 85–88 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hofmann, H., Sakti, S., Isotani, R., Kawai, H., Nakamura, S., Minker, W. (2010). Sequence-Based Pronunciation Modeling Using a Noisy-Channel Approach. In: Lee, G.G., Mariani, J., Minker, W., Nakamura, S. (eds) Spoken Dialogue Systems for Ambient Environments. IWSDS 2010. Lecture Notes in Computer Science(), vol 6392. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16202-2_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-16202-2_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16201-5
Online ISBN: 978-3-642-16202-2
eBook Packages: Computer ScienceComputer Science (R0)