Effect of high-frequency spectral components in computer recognition of dysarthric speech based on a Mel-cepstral stochastic model

Journal of Rehabilitation Research and Development

Volumn 42, Issue 3, 2005, Pages 363-371

  Polur, Prasad D ^a   Miller, Gerald E ^a  

^a Virginia Commonwealth University   (United States)

Author keywords

Cerebral palsy; Communication disorder; Dysarthric speech; Hidden Markov model; High frequency spectral components; Human machine interfaces; Mel frequency cepstral coefficients; Rehabilitation; Speech and motor disabilities; Speech recognition

Indexed keywords

COMPUTER APPLICATIONS; DATA REDUCTION; FREQUENCIES; MARKOV PROCESSES; RELIABILITY; SPECTRUM ANALYSIS; SPEECH RECOGNITION;

CEREBRAL PALSY; DYSARTHRIA; HIDDEN MARKOV MODEL (HMM); SPEECH PATTERNS;

PATIENT REHABILITATION;

ACOUSTICS; ARTICLE; CEREBRAL PALSY; COMPUTER ANALYSIS; DYSARTHRIA; FREQUENCY ANALYZER; MAN MACHINE INTERACTION; MOTOR DYSFUNCTION; PERFORMANCE; PRIORITY JOURNAL; SPECTROSCOPY; SPEECH DISCRIMINATION; STATISTICAL MODEL; STOCHASTIC MODEL;

ARTIFICIAL INTELLIGENCE; CEREBRAL PALSY; COMMUNICATION AIDS FOR DISABLED; DYSARTHRIA; HUMANS; MALE; MARKOV CHAINS; MODELS, THEORETICAL; SIGNAL PROCESSING, COMPUTER-ASSISTED; SPEECH ACOUSTICS; SPEECH INTELLIGIBILITY; SPEECH PRODUCTION MEASUREMENT; SPEECH RECOGNITION SOFTWARE;

EID: 23344451808     PISSN: 07487711     EISSN: None     Source Type: Journal    
DOI: 10.1682/JRRD.2004.06.0067     Document Type: Article

References (14)

1. Menendez-Padial X, Polikoff JB, Peters SM, Leonzio JE, Bunnell HT. The Nemours database of dysarthric speech. Proceedings of the 4th International Conference on Spoken Language Processing (ICSLP), 1996 October 3-6, Philadelphia (PA). Wilmington (DE): Applied Science and Engineering Laboratories; 1996. p. 1962-65.
2. Gold CJ. Cerebral palsy-John Coopersmith Gold. Berkeley Heights (NJ): Enslow Publishers, Inc.; 2001.
3. Noyes JM, Prankish CR. Speech recognition technology for individuals with disabilities. Augmentative Altern Commun. 1992;8:297-303.
4. Sy BK, Horowitz DM. A statistical causal model for the assessment of dysarthric speech and the utility of computer based speech recognition. IEEE Trans Biomed Eng. 1993; 40(12):1282-98.
5. Patel R. Identifying information bearing prosodie parameters in severely dysarthric speech [dissertation]. University of Toronto (Canada); 2000.
6. Goodenough C, Rosen M. Towards a method for computer interface design using speech recognition. Proceedings of the 14th Annual Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) Conference, 1991, Kansas City (MO). Arlington (VA): RESNA Press; 1991. p. 328-29.
7. Jayaram G, Abdelhamied K. Experiments in dysarthric speech recognition using artificial neural networks. J Rehabil Res Dev. 1995;32(2):162-69.
8. Deller JR Jr, Hsu D, Ferrier LJ. On the use of hidden Markov modeling for recognition of dysarthric speech. Comput Methods Programs Biomed. 1991;35(2):125-39.
9. Chen F, Kostov A. Optimization of dysarthric speech recognition. Proceedings of the 19th Annual International Conference of the Institute of Electrical and Electronics Engineers, Inc. (IEEE), 1997 October 30-November 2, Chicago (IL). Piscataway (NJ): IEEE; 1997. p. 1436-39.
10. Kain A, Niu X, Hosom J, Miao Q, Santen J. Formant resynthesis of dysarthric speech. Center for Spoken Language Understanding, Oregon Graduate Institute School of Science and Engineering, Oregon Health and Science University, Portland (OR), 2004 [cited May 2005]. Available from: http://www.cslu.ogi.edu/~kain/tts2004/kain.pdf/
11. Mak B, Tarn YC, Li Q. Discriminative auditory-based features for robust speech recognition. IEEE Trans Speech Audio Proc. 2004;12(1):27-36.
12. Rabiner LR. A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE. 1989;77(2):257-86.
13. Jelinek F. Statistical methods for speech recognition. Language, speech and communication: a Bradford book. Cambridge (MA): The MIT Press; 1998. p. 15-54, p. 79-90, p. 147-163.
14. Kavcic A, Jose Moura MF. The Viterbi algorithm and Markovian noise memory. IEEE Trans Inf Theory. 2000; 46(1):291-301.