Validation techniques for parallel feature streams: the case of phoneme identification for speech recognition

• Autorzy: Aioanei, D. , Neugebauer, M. , Carson-Berndsen, J.
• Konferencja: Human Language Technologies as a challenge for Computer Science and Linguistics (2; 21-23.04.2005; Poznań, Poland)
• Języki publikacji: EN

Abstrakty

EN

This paper presents an approach to the phonetic interpretation of multilinear feature representations of speech utterances combining linguistic knowledge and efficient computational techniques. Multilinear feature representations are processed as intervals and the linguistic knowledge used by the system takes the form of feature implication rules (constraints) represented as subsumption hierarchies which are used to validate each interval. In the case of noisy or underspecified data, the linguistic constraints can be used to enrich the representations. Experiments are also presented to show that the system is logically correct and does not introduce errors in the data, and that it deals with underspecified and noisy input.

Słowa kluczowe

EN

automatic speech recognition; articulatory features

• Czasopismo: Archives of Control Sciences
• Rocznik: 2005
• Tom: Vol. 15, no. 3
• Strony: 279--290
• Opis fizyczny: Bibliogr. 13 poz., rys.

Twórcy

autor

Aioanei, D.

• School of Computer Science and Informatics, University College Dublin, Ireland,

autor

Neugebauer, M.

• School of Computer Science and Informatics, University College Dublin, Ireland,

autor

Carson-Berndsen, J.

• School of Computer Science and Informatics, University College Dublin, Ireland,

Bibliografia

• [1] A. M. A. Ali, J. van der Spiegel, P. Mueller, G. Haentjens and . J. Berman: An acoustic-phonetic feature-based system for automatic phoneme recognition in continuous speech. In IEEE Int’l Symp. on Circuits and Systems. III (1999), 118-121.
• [2] J. Carson-Berndsen: Time Map Phonology: Finite State Models and Event Logics in Speech Recognition. Kluwer Academic Publishers. Holland, 1998.
• [3] J. Carson-Berndsen and M. Walsh: Phonetic lime maps: Defining constraints for multilinear speech processing. In van Dommelen & Barry. (Ed), The integration of Phonetic Knowledge Speech Technology. Kluwer. 2005.
• [4] J. Frankel, M. WESTER and S. King: Articulatory feature recognition using dynamic Bayesian networks. In Proc. of ICSLP, (2004).
• [5] B. Ganter and R. Wille: Formal Concept Analysis: Mathematical Foundations. Springer Verlag. Berlin, 1999.
• [6] J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, D. S. Pallett and N. L. Dahlgren: The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus. NIST, 1993.
• [7] A. Juneja and C. Espy-Wilson: An event-based acoustic-phonetic approach to speech segmentation and e-set recognition. In Proc. 15th Int. Congress of Phonetic Sciences. Universität Autonoma de Barcelona, (2003).
• [8] K. Kirchhoff: Robust Speech Recognition Using Articulatory- Information. PhD thesis, University of Bielefeld, 1999.
• [9] M. Neugebauer: Machine Learning and Phonological Classification. In Proc. TAAL Postgraduate Conf., University of Edinburgh, (2003).
• [10] NIST. sctk-1.3 speech recognition scoring toolkit. In www.nist.gov/speech/iitoh, 1996.
• [11] W. Petersen: A set-theoretical approach for the induction of inheritance hierarchies. In Proc. Joint Conf. on Formal Grammar and Mathematics of language. Electronic Notes in Theoretical Computer Science. Springer, (2001).
• [12] C. Sporleder: Learning lexical inheritance hierarchies with maximum entropy models. In Workshop on Machine Learning Approaches in Computational Linguistics at ESSLII 2002, Trento, (2002).
• [13] S. Young, G. Evermann, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev and P. Woodland: The HTK Book (for HTK Version 3.2.1), 2002.