Abstract
The main goal of this work is the adaptation of a broadcast news transcription system to a new domain, namely, the Portuguese Parliament plenary meetings. This paper describes the different domain adaptation steps that lowered our baseline absolute word error rate from 20.1% to 16.1%. These steps include the vocabulary selection, in order to include specific domain terms, language model adaptation, by interpolation of several different models, and acoustic model adaptation, using an unsupervised confidence based approach.
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
Gales, M., Kim, D., Woodland, P., Mrva, D., Sinha, R., Tranter, S.: Progress in the CU-HTK Broadcast News Transcription System. IEEE Transactions on Audio Speech and Language Processing (2006)
Sinha, R., Gales, M., Kim, D., Liu, X., Sim, K., Woodland, P.: The CU-HTK Mandarin Broadcast New Transcription System. In: Proceedings ICASSP (2006)
Nguyen, L., Abdou, S., Afify, M., Makhoul, J., Matsoukas, S., Schwartz, R., Xiang, B., Lamel, L., Gauvain, J., Adda, G., Schwenk, H., Lefevre, F.: The 2004 BBN/LIMSI 10xRT English Broadcast News Transcription System. In: Proceedings DARPA RT 2004, Palisades, NY (November 2004)
Lamel, L., Gauvain, J., Adda, G., Barras, C., Bilinski, E., Galibert, O., Pujol, A., Schwenk, H., Zhu, X.: The LIMSI 2006 TC-STAR EPPS Transcription Systems. In: Proceedings of ICASSP, Honolulu, Hawaii, pp. 997–1000 (April 2007)
Ramabhadran, B., Siohan, O., Mangu, L., Zweig, G., Westphal, M., Schulz, H., Soneiro, A.: The IBM 2006 Speech Transcription System for European Parliamentary Speeches. In: ICSLP (September 2006)
Kiss, I., Leppanen, J., Sivadas, S.: Nokia’s system for TC-STAR EPPS English ASR evaluation task. In: Proceedings of TC-STAR Speech-to-Speech Translation Workshop, Barcelona, Spain (June 2006)
Meinedo, H., Caseiro, D., Neto, J., Trancoso, I.: AUDIMUS.media: a Broadcast News speech recognition system for the European Portuguese language. In: Mamede, N.J., Baptista, J., Trancoso, I., Nunes, M.d.G.V. (eds.) PROPOR 2003. LNCS, vol. 2721. Springer, Heidelberg (2003)
Meinedo, H., Neto, J.: Combination of acoustic models in continuous speech recognition. In: Proceedings ICSLP 2000, Beijing, China (2000)
Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. In: ASR 2000 Workshop (2000)
Martins, C., Teixeira, A., Neto, J.: Language models in automatic speech recognition. Magazine of DET-UA. Aveiro 4(4) (2005)
Meinedo, H.: Audio pre-processing and speech recognition for Broadcast News. PhD thesis, IST (2008)
Martins, C., Teixeira, A., Neto, J.: Dynamic Broadcast News transcription system. In: ASRU 2007 (2007)
Caseiro, D., Trancoso, I., Oliveira, L., Viana, C.: Grapheme-to-phone using finite state transducers. In: Proc. 2002 IEEE Workshop on Speech Synthesis, Santa Monica, CA, USA (2002)
Stolcke, A.: Srlim - an extensible language modeling toolkit. In: Proc. ICSLP 2002, Denver, USA (2002)
Souto, N., Meinedo, H., Neto, J.: Building language models for continuous speech recognition systems. In: Ranchhod, E., Mamede, N.J. (eds.) PorTAL 2002. LNCS (LNAI), vol. 2389. Springer, Heidelberg (2002)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Neves, L., Martins, C., Meinedo, H., Neto, J. (2008). Domain Adaptation of a Broadcast News Transcription System for the Portuguese Parliament. In: Teixeira, A., de Lima, V.L.S., de Oliveira, L.C., Quaresma, P. (eds) Computational Processing of the Portuguese Language. PROPOR 2008. Lecture Notes in Computer Science(), vol 5190. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85980-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-85980-2_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85979-6
Online ISBN: 978-3-540-85980-2
eBook Packages: Computer ScienceComputer Science (R0)