Speech Recognition and Coding pp 84-87 | Cite as
Acoustic-Phonetic Decoding of Spanish Continuous Speech with Hidden Markov Models
Conference paper
Abstract
This work is aimed to present the state of the acoustic phonetic decoding of Spanish continuous speech in the Hidden Markov Modelling (HMM) framework. We will discuss two different choices of sub-lexical units we made for a Spanish decoder phone-like units and discriminative-transitional/steady units. Within the framework of HMM, we will report different series of decoding experiments of Spanish continuous speech. Single and multiple codebook experiments will be present within both the classical discrete approach and the more recently developed Semicontinuous one.
Keywords
Hide Markov Modelling Speech Recognition Vector Quantization Continuous Speech Recognition Cepstrum Coefficient
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- [1]P. Bamberg, A. Demedts, J. Elder, C. Huang, C. Ingold, M. Mandel, L. Manganaro and S. van Even. “Phoneme-based Training for Large-vocabulary recognition in six European Languages”. Proc. Eurospeech (1991), pp, 175–181Google Scholar
- [2]E. Lleida, J.B. Mariño, C. Nadeu, J. Salavedra. “Demisylliable-based HMM spotting for continuous speechrecognition”. Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (1991), pp. 709–712Google Scholar
- [3]J. Llisterri. “Criterios para la elaboración de una base de datos para el reconocimiento del habla en espanol”. ALBAYZIN Technical Report, 1991Google Scholar
- [4]SAM. “Multi-lingual Speech input/output assessment, methodology and standardisation”. Esprit project 2589 (SAM). ESPRIT Technical Report, 1991Google Scholar
- [5]I. Torres. “Selección de unidades subléxicas para la decodificación acústico-fonética del habla en Castellano”Internal Report of D.S.J.C. Universidad Politécnica de Valencia, 1992Google Scholar
- [6]C.H. Lee, L.R. Rabiner, R. Pieraccini and J.G. Wilpon. “Acoustic modeling for large vocabulary Speech Recognition”. Computer Speech and Language (1990) 4, pp. 127–165CrossRefGoogle Scholar
- [7]X.D. Huang. “Phoneme Classification Using Semicontinuous Hidden Markov Models”. IEEE Trans. Acoust., Speech, Signal Processing (1992), vol. 40, No. 5, pp. 1062–1067CrossRefGoogle Scholar
- [8]J.M. Koo, H.S. Lee, C.K. Un. “An improved VQ codebook design algorithm for HMM”. Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (1992) 1-357-360Google Scholar
- [9]B. Plannerer and G. Ruske. “Recognition of demisy liable based units using semicontinuous Hidden Markov Models”. Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (1992) 1-581-584Google Scholar
- [10]I. Torres, F. Casacuberta “Spanish Phone Recognition using Semicontinuous Hidden Markov Models”. Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (1993), pp. II–515, 518Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 1995