Abstract
This paper investigates the tandem architecture (TA) based on segmental features. The segmental feature based recognition system has been reported to show better results than the conventional feature based system in previous studies. In this paper we tried to merge the segmental feature with the tandem architecture which uses both hidden Markov models and neural networks. In general, segmental features can be separated into the trend and location. Since the trend means variation of segmental features and since it occupies a large portion of segmental features, the trend information was used as an independent or additional feature for the speech recognition system. We applied the trend information of segmental features to TA and used posterior probabilities, which are the output of the neural network, as inputs of the recognition system. Experiments were performed on Aurora2 database to examine the potentiality of the trend feature based TA. The results of our experiments verified that the proposed system outperforms the conventional system on very low SNR environments. These findings led us to conclude that the trend information on TA can be additionally used for the traditional MFCC features.
He was a visiting researcher at ETRI from May 2006 to Feb. 2007.
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
Deng, L.: A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal. Signal Processing 27, 65–78 (1992)
Gish, H., Ng, K.: A segmental speech model with application to word spotting. In: Proc. of Int. Conf. on Acoustics, Speech and Signal Proc. vol. II, pp. 447–450 (1993)
Gales, M.J.F., Young, S.J.: Segmental Hidden Markov Models. In: Proc. of European Conf. on Speech Comm. and Tech., pp. 1579–1582 (1993)
Gish, H., Ng, K.: Parametric trajectory models for speech recognition. In: Proc. of Int. Conf. on Spoken Lang. Proc. vol. I, pp. 466–469 (1996)
Ostendorf, M., Digalakis, V., Kimball, O.A.: From HMMs to Segment Models: A Unified View of Stochastic Modeling for Speech Recognition. IEEE Tr. on Speech and Audio Processing 4(5), 360–378 (1996)
Holmes, W.J., Russell, M.J.: Probabilistic trajectory segmental HMMs. Computer Speech and Language 13, 3–37 (1999)
Yun, Y.S., Oh, Y.H.: A Segmental-Feature HMM for Speech Pattern Modeling. IEEE Signal Processing Letters 7(6), 135–137 (2000)
Yun, Y.S., Oh, Y.H.: A Segmental-Feature HMM for Continuous Speech Recognition Based On a Parametric Trajectory Model. Speech Communication 38(1), 115–130 (2002)
Yun, Y.S.: Sharing Trend Information of Trajectory in Segmental Feature HMM. In: Proc. of Int. Conf. On Spoken Language Proc., Denver, Colorado, USA, pp. 2641–2644 (2002)
Hermansky, H., Ellis, D., Sharma, S.: Tandem connectionist feature extraction for conventional HMM systems. In: Proc. of Int. Conf. on Acoustics, Speech and Signal Proc., Istanbul, Turkey, pp. 1635–1638 (2000)
Ellis, D.W.P., Singh, R., Sivadas, S.: Tandem acoustic modeling in large-vocabulary recognition. In: Proc. of Int. Conf. on Acoustics, Speech and Signal Proc., Salt Lake City, USA, pp. 517–520 (2001)
Sivadas, S., Hermansky, H.: Generalized Tandem Feature Extraction. In: Proc. of Int. Conf. on Acoustics, Speech and Signal Proc. vol. II, pp. 56–59 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yun, YS., Lee, Y. (2007). Design of Tandem Architecture Using Segmental Trend Features. In: Matoušek, V., Mautner, P. (eds) Text, Speech and Dialogue. TSD 2007. Lecture Notes in Computer Science(), vol 4629. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74628-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-540-74628-7_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74627-0
Online ISBN: 978-3-540-74628-7
eBook Packages: Computer ScienceComputer Science (R0)