Phoneme recognition based on hybrid neural networks with inhibition/enhancement of distinctive phonetic feature (DPF) trajectories

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 1529-1532

  Huda, Mohammad Nurul ^a   Katsurada, Kouichi ^a   Nitta, Tsuneo ^a  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

Distinctive phonetic feature; Inhibition enhancement network; Local features; Multi layer neural network; Recurrent neural network

Indexed keywords

CO-ARTICULATION; DISTINCTIVE PHONETIC FEATURE; DYNAMIC PATTERNS; EXTRACTION METHOD; HYBRID NEURAL NETWORKS; INHIBITION/ ENHANCEMENT NETWORK; LOCAL FEATURE; MIXTURE COMPONENTS; PHONEME RECOGNITION; TWO STAGE;

FEATURE EXTRACTION; LINGUISTICS; RECURRENT NEURAL NETWORKS; SPEECH COMMUNICATION; TRAJECTORIES;

NETWORK LAYERS;

EID: 84867225573     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. I. Bazzi and J. R. Glass, "Modeling OOV words for ASR," Proceedings of ICSLP, Beijing, China, p. 401-404, 2000.
2. S. Seneff, et. al, "A two-pass for strategy handling OOVs in a large vocabulary recognition task," Proc. Interspeech, 2005.
3. K. Kirchhoff "OOV Detection by Joint Word/Phone Lattice Alignment ," ASRU , Kyoto, Japan, Dec 2007.
4. D.J Pepper, et. al, "Phonemic recognition using a large hidden Markov model," IEEE Transactions, Volume 40, Issue 6, June 1992.
5. B. Merialdo (1988), "Phonetic Recognition Using Hidden Markov Models and Maximum Mutual Information Training,"Proc. IEEE ICASSP-88, pp. 111-114.
6. K. Kirchhoff, et. al, "Combining acoustic and articulatory feature information for robust speech recognition," Speech Commun.,vol.37, pp.303-319, 2002.
7. T. Fukuda, et al, "Orthogonalized DPF extractor for Noise-robust ASR," IEICE Trans., vol.E87-D, no.5, pp.1110-1118, 2004.
8. N. Huda, et al, "Distinctive Phonetic Feature (DPF) Based Phone Segmentation using Hybrid Neural Networks," Proc. Interspeech 2007, pp.94-97, 2007.
9. T. Robinson, "An application of Recurrent Nets to Phone Probability Estimation," IEEE Trans. Neural Networks, Volume 5, Number 3, 1994.
10. S. King and P. Taylor, "Detection of Phonological Features in Continuous Speech using Neural Networks," Computer Speech and Language 14(4), pp. 333-345, 2000.
11. E. Eide, "Distinctive Features for Use in an Automatic Speech Recognition System," Proc. Eurospeech 2001, vol.III, pp.1613-1616, 2001.
12. JNAS: Japanese Newspaper Article Sentences. http://www.milab.is.tsukuba. ac.jp/jnas/instruct.html.