Abstract
A multilingual long audio alignment system is presented in the automatic subtitling domain, supporting English, Spanish and Basque. Pre-recorded contents are recognized at phoneme level through language-dependent triphone-based decoders. In addition, the transcripts are phonetically translated using grapheme-to-phoneme transcriptors. An optimized version of Hirschberg’s algorithm performs an alignment between both phoneme sequences to find matches. The correctly aligned phonemes and their time-codes obtained in the recognition step are used as the reference to obtain near-perfectly aligned subtitles. The performance of the alignment algorithm is evaluated using different non-binary scoring matrices based on phone confusion-pairs from each decoder, on phonological similarity and on human perception errors. This system is an evolution of our previous successful system for long audio alignment.
This is a preview of subscription content, log in via an institution to check access.
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
Álvarez, A., Arzelus, H., Ruiz, P.: Long audio alignment for automatic subtitling using different phone-relatedness measures. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Florence, Italy (2014)
Moreno, P.J., Joerg, C., Van Thong, J.-M., Glickman, O.: A recursive algorithm for the forced alignment of very long audio segments. In: Proceedings of the 5th International Conference on Spoken Language Processing, ICSLP, Sydney, Australia (1998)
Lecouteux, B., Linàres, G., Nocéra, P., Bonastre, J.: Imperfect transcript driven speech recognition. In: Proceedings of INTERSPEECH, pp. 1626–1629 (2006)
Bordel, G., Nieto, S., Peñagarikano, M., Rodríguez-Fuentes, L.J., Varona, A.: A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions. In: Proceedings of INTERSPEECH, Portland, Oregon (2012)
Hirschberg, D.S.: A linear space algorithm for computing maximal common subsequences. Communications of the ACM 18(6), 341–343 (1975)
Kondrak, G.: Algorithms for Language Reconstruction. PhD Thesis. University of Toronto (2002)
Comas, P.: Factoid Question Answering for Spoken Documents. PhD Thesis. Universitat Politècnica de Catalunya (2012)
Cutler, A., Weber, A., Smits, R., Cooper, N.: Patterns of English phoneme confusions by native and non-native listeners. Journal of the Acoustical Society of America 116(6), 3668–3678 (2004)
García Lecumberri, M.L., Toth, A.M., Tang, Y., Cooke, M.: Elicitation and analysis of a corpus of robust noise-induced word misperceptions in Spanish. In: Proceedings of INTERSPEECH, pp. 2807–2811 (2013)
Garafolo, J.S.L., Fisher, W., Fiscus, J., Pallett, D., Dahlgren, N., Zue, V.: TIMIT Acoustic-Phonetic Continuous Speech Corpus. Linguistic Data Consortium, Philadelphia (1993)
Díaz, J.E., Peinado, A., Rubio, A., Segarra, E., Prieto, N., Casacuberta, F.: Albayzín: a task-oriented Spanish speech corpus. In: Proceedings of LREC, Granada, Spain (1998)
Campione, E., Véronis, J.: A multilingual prosodic database. In: Proceedings of the 5th International Conference on Spoken Language Processing, ICSLP, Sydney, Australia (1998)
Del Pozo, A., Aliprandi, C., Álvarez, A., Mendes, C., Neto, J.P., Paulo, S., Piccinini, N., Rafaelli, M.: SAVAS: Collecting, Annotating and Sharing Audiovisual Language Resources for Automatic Subtitling. In: Proceedings of LREC, Reykjavik, Iceland (2014)
Ladefoged, P.: A Course in Phonetics. Harcourt Brace Jovanovich, New York (1995)
Ruiz, P., Álvarez, A., Arzelus, H.: Phoneme similarity matrices to improve long audio alignment for automatic subtitling. In: Proceedings of LREC, Reykjavik, Iceland (2014)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Álvarez, A., Ruiz, P., Arzelus, H. (2014). Improving a Long Audio Aligner through Phone- Relatedness Matrices for English, Spanish and Basque. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2014. Lecture Notes in Computer Science(), vol 8655. Springer, Cham. https://doi.org/10.1007/978-3-319-10816-2_57
Download citation
DOI: https://doi.org/10.1007/978-3-319-10816-2_57
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10815-5
Online ISBN: 978-3-319-10816-2
eBook Packages: Computer ScienceComputer Science (R0)