Performance of Isolated Digit Speech Recognition in Crowded Environment.
Speech recognition is a process that recognizes what the speaker says. Its objective is to extract, characterize and recognize the information in the speech signal conveying what the speaker says. One of major problems in speech recognition domain is disturbance caused by background noise. This dist...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | eng eng |
Published: |
2007
|
Subjects: | |
Online Access: | https://etd.uum.edu.my/123/1/Muhamad_Arif_Hashim.pdf https://etd.uum.edu.my/123/2/Muhamad_Arif_Hashim-1.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-uum-etd.123 |
---|---|
record_format |
uketd_dc |
institution |
Universiti Utara Malaysia |
collection |
UUM ETD |
language |
eng eng |
topic |
TK Electrical engineering Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering Electronics Nuclear engineering Muhamad Arif, Hashim Performance of Isolated Digit Speech Recognition in Crowded Environment. |
description |
Speech recognition is a process that recognizes what the speaker says. Its objective is to extract, characterize and recognize the information in the speech signal conveying what the speaker says. One of major problems in speech recognition domain is disturbance caused by background noise. This disturbance can decrease the effectiveness and reliability of the system and its accuracy. This research objective is to measure the
performance of isolated digit speech recognition in crowded environment. VQSR prototype uses two kinds of distance measure: Euclidean distance and city block
distance. Noisy digit speech, which is constructed from TIDigit speech database and cafeteria noise from CLSU database, is used to train and test the prototype. The
prototype is also tested using real data that been recorded in a crowded and noisy cafeteria. Results of training and testing phases are recorded and compared between these two distance measures using a set of performance measurement analysis. This set includes Sensitivity, Specificity, Total Accuracy, False Acceptance Rate, False Rejection Rate and Half Total Error Rate analysis. Based on the performance measurement, a robust and reliable digit speech can be used by user that has high
possibility of success and low probability in making errors. Finally, the proposed model and guideline in evaluating the digit speech performance can be use in other speech domain. |
format |
Thesis |
qualification_name |
masters |
qualification_level |
Master's degree |
author |
Muhamad Arif, Hashim |
author_facet |
Muhamad Arif, Hashim |
author_sort |
Muhamad Arif, Hashim |
title |
Performance of Isolated Digit Speech Recognition in Crowded Environment. |
title_short |
Performance of Isolated Digit Speech Recognition in Crowded Environment. |
title_full |
Performance of Isolated Digit Speech Recognition in Crowded Environment. |
title_fullStr |
Performance of Isolated Digit Speech Recognition in Crowded Environment. |
title_full_unstemmed |
Performance of Isolated Digit Speech Recognition in Crowded Environment. |
title_sort |
performance of isolated digit speech recognition in crowded environment. |
granting_institution |
Universiti Utara Malaysia |
granting_department |
College of Arts and Sciences (CAS) |
publishDate |
2007 |
url |
https://etd.uum.edu.my/123/1/Muhamad_Arif_Hashim.pdf https://etd.uum.edu.my/123/2/Muhamad_Arif_Hashim-1.pdf |
_version_ |
1747826824570732544 |
spelling |
my-uum-etd.1232013-07-24T12:05:40Z Performance of Isolated Digit Speech Recognition in Crowded Environment. 2007-08-05 Muhamad Arif, Hashim College of Arts and Sciences (CAS) Faculty of Information Technology TK Electrical engineering. Electronics Nuclear engineering Speech recognition is a process that recognizes what the speaker says. Its objective is to extract, characterize and recognize the information in the speech signal conveying what the speaker says. One of major problems in speech recognition domain is disturbance caused by background noise. This disturbance can decrease the effectiveness and reliability of the system and its accuracy. This research objective is to measure the performance of isolated digit speech recognition in crowded environment. VQSR prototype uses two kinds of distance measure: Euclidean distance and city block distance. Noisy digit speech, which is constructed from TIDigit speech database and cafeteria noise from CLSU database, is used to train and test the prototype. The prototype is also tested using real data that been recorded in a crowded and noisy cafeteria. Results of training and testing phases are recorded and compared between these two distance measures using a set of performance measurement analysis. This set includes Sensitivity, Specificity, Total Accuracy, False Acceptance Rate, False Rejection Rate and Half Total Error Rate analysis. Based on the performance measurement, a robust and reliable digit speech can be used by user that has high possibility of success and low probability in making errors. Finally, the proposed model and guideline in evaluating the digit speech performance can be use in other speech domain. 2007-08 Thesis https://etd.uum.edu.my/123/ https://etd.uum.edu.my/123/1/Muhamad_Arif_Hashim.pdf application/pdf eng validuser https://etd.uum.edu.my/123/2/Muhamad_Arif_Hashim-1.pdf application/pdf eng public masters masters Universiti Utara Malaysia Adda-Decker, M., Antoine, F., Boula de Mareuil, P., Vasilescu, I., Lamel, L., Vaissiere, J., Geoffrois, J. & Lienard,. J. S. (2003). Phonetic knowledge, phonotactics and perceptual validation for automatic language identification. Proc. 15th ICPhS, Barcelona. Aida-Zade, K. R., Ardil, C. & Rustamov, S. S. (2006). Investigation of Combined use of MFCC and LPC Features in Speech Recognition Systems. International Journal of signal Processing, 3 (2). 105-111. Bengio, S., Keller, M. & Mari'ethoz J. (2005). The Expected Performance Curve. International Conference on Machine Learning, ICML, Workshop on ROC Analysis in Machine Learning, Bonn, Germany. Bishop, C. (1995). Neural network for pattern recognition. Oxford University Press. Bourouba, E. H., Bedda, M. & Djemili, R. (2006). Isolated Words Recognition System Based on Hybrid Approach DTW/GHMM. Informatics. 373-384. Campbell, J. P. (1997). Speaker Recognition: A Tutorial. Proceedings of the IEEE, 85 (9). 1437-1462. Chien, J. & Furui, S. (2005). Predictive Hidden Markov Model Selection for Speech Recognition. IEEE Transactions on Speech and Audio Processing, 13(3). 377-387. Common Criteria Biometric Evaluation Methodology Working Group. (2002). Common Methodology for Information Technology Security Evaluation (version 1.0). Retrieved May 13, 2006, from http://www.cesg.gov.uk/site/ast/biometrics/media/BEM_10.pdf Cook, S. (2002). Speech Recognition HOWTO. Retrieved Retrieved October 3, 2006, from http://www.ibiblio.org/pub/linux/docs/HOWTO/other-formats/pdf/Speech-Recognition-HOWTO.pdf Cosi, et al. (1998). Connected Digit Recognition Experiments with the OGI Toolkit's Neural Network and HMM-Based Recognizer. Interactive Voice for Telecommunication Applications, IVTTA '-98, 135-140. Chitu, A. G. et al. (2007). Comparison between Different Feature Extraction Techniques for Audio-Visual Speech Recognition. Journal on Multimodal Interfaces, pp. 16, Springer. Ephraim, Y., Lev-Ari, H. & Roberts, W. J. J. (2005). A brief survey of speech enhancement. CRC Electronic Handbook, 2nd edition, CRC Press. Fluency Voice. (2007). Consumers give their voice to speech recognition. FST. Retrieved March 1, 2007, from http://www.gdsinternational.com/infocentre/artsum.asp?mag= 187&iss=183&art=268962&lang=en Forsberg, M. (2003). Why is Speech Recognition Difficult?. Retrieved March 1,2007, from http://www.speech.kth.se/~roIf/gslt_ papers/ MarkusForsberg.pdf Furui, S. (2005). 50 years of progress in speech and speaker recognition. Proc. SPECOM 2005. 1-9. Gavat, I., Zirra, M. & Enescu, V. (1996). A Hybrid NN-HMM System for Connected Digit Recognition over Telephone in Romanian Language. Third IEEE Workshop on Interactive Voice Technology for Telecommunications Applications.37-40. Grasso, M. A. (2003). The Long-Term Adoption of Speech Recognition in Medical Applications. Proceedings of the 16th IEEE Symposium on Computer-Based Medical Systems, CBMS'03. 257 - 262. Hedberg, S.R. (1997). Dictating this article to my computer: automatic speech recognitionis coming of age. IEEE Intelligent Systems and Their Applications, 12(6). 9-11. Hennebert, J., Hasler, M. & Dedieu, H. (1993). Neural Networks in Speech Recognition. Retireved February 11, 2005, from http://citeseer.ist.psu.edu/cache/papers/cs/3630/http:zSzzSzcircwww.epfl.chzSzstaffSzSzhenneberzSzjeanzSzpapierszSzMicrocompzSzneuralnet.pdf/neural-networks-in-speech.pdf Hunt, M. J. (1999). Spectural signal processing for ASR. Proc. ASRU'99. Juang, B.H., D. Childers, R.V. Cox, R. De Mori, S. Furui, J. Mariani, P. Price, S.Sagayama, M.M. Sondhi, & R. Weishedel. (1998). Speech Processing: Past, Present and Outlook. IEEE Signal Processing Magazine, May 1998. Kasper, K. et al. (1995). A fully recurrent neural network for recognition of noisy telephone speech. International Conference on Acoustics, Speech, and Signal Processing, I995. ICASSP-95. vol.5.3331 - 3334. Kinnunen, T., Karpov, E. & Franti, P. (2006). Real-Time Speaker Identification and Verification. IEEE Transactions on Audio, Speech, and Language Processing. 14(1). 277-288. Kirchhoff, K. & Parandekar, S. (2001). Multi-stream statistical language modeling with application to automatic language identification. Proceedings of Eurospeech O1. 803-806. Kirchhoff, K., Parandekar, S. & Bilmes, J. (2002). Mixed-Memory Markov Models for Automatic Language Identification. IEEE International. Conference on Acoustics, Speech, and Signal Processing, Proceedings of ICASSP'02, 1. 761-764. Klusacek, D., Navratil, J., Reynolds, D. & Campbell, J. (2003). Conditional Pronunciation Modeling In Speaker Detection. IEEE International. Conference on Acoustics, Speech, and Signal Processing, Proceedings of ICASSP '03,4. 804-807. Levy, C., Linares, G. & Nocera, P. (2003). Comparison of Several Acoustic Modeling Techniques and Decoding Algorithms for Embedded Speech Recognition Systems. 2003 Workshop on DSP in Mobile and Vehicular Systems. Nagoya, Japan. Low, R. & Togreri. (1998). Speech Recognition Using the Probabilistic Neural Network. Proceedings of ICSLP98 (SST Student Day), Sydney, Australia. Lockwood, P. & Boudy, J. (1991). Experiments with a Non-linear Spectral Subtractor (NSS), Hidden Markov Models and the Projection, for Robust Speech Recognition in Cars. Proceedings European Conference on Speech Communication and Technology, Proc. EUROSPEECH..79-82. Md. Rashidul Hasan et.al. (2004). Speaker Identification using Me1 Frequency Cepstral Coefficient. 3rd International Conference on Electrical & Computer Engineering, ICECE 2004. 565-568. Miller, D. R. H., Leek, T. & Schwartz, R. M. (1999). A Hidden Markov Model Information Retrieval System. 22nd ACM International Conference on Research and Development in Information Retrieva, Proceedings of SIGIR-99.214-221. Mohri, M. & Riley, M. (1997). Weighted Determination and Minimization for Large Vocabulary Speech Recognition. Proceedings European Conference on Speech Communication and Technology, Proc. Eurospeech'97, 1.131-134. Mut, 0. & Gokturk, M. (2005). Improved Weighted Matching for Speaker Recognition. Transactions on Engineering, Computing and Technology. 5.229-231. O'gorman, L. (2003). Comparing Passwords, Tokens and Biometries for User Authentication. Proceedings of the IEEE, 91(12). 2019-2020. Orman, 0. D. & Arslan, L. M., (2001). Frequency Analysis of speaker Identification. 2001 Speaker Odyssey. Owens, F.J. (1993). Signal processing of speech, Macmillan. Paliwal, K. & Atal,B.(1993). Efficient Vector Quantization of LPC Parameters at 24 Bits/Frame. IEEE Transactions on Speech and Audio Processing, 1(1). 3-14. Pearce, D. & Hirsch, H. (2000). The Aurora Experimental Framework for the Performance Evaluation of Speech Recognition Systems under Noisy Conditions. 6th International Conference on Spoken Language Processing, ICSLP 2000. 181-188. Perez, E. & Rodriguez-Esteban, R. (2004). Oreja ... for the design of psychoacoustic experiments (Manual User's version 1.0). Retrieved October 2, 2005, from http://www.ee.columbia.edu/~raul/oreja/manual.htm Picone, J. (1996). Fundamentals of Speech Recognition: A Short Course. Retrieved October 2,2005, from http://www.stillhq.com/diary/asr-shofl.pdf Rabiner L.R. & Juang B.H. (1993). Fundamentals of speech recognition. Prentice-Hall, Englewood Cliffs, NJ. Raiko, T.(2003). Speech recognition in noisy environments: A survey. Retrieved February 11, 2005, from http://www.cis.hut.fi/Opinnot/T-61.6020/2003/ Kalvot2003/raiko1.pdf Rodrigues, F. & Trancoso, I. (1999). Digit Recognition Using the SPEECHDAT Corpus.Conference on Telecommunications ,CONFTELE'99. Saldana, I. & Ginberg, D. (2003). Remote Speaker and Speech Recognition : A senior design project. Retrieved August 11, 2005, from http://www.yov408.com/tutorials/speech_recog.pdf Savage, J., Rivera, C. & Aguilar, V. (1998). Isolated Word Speech Recognition using Vector Quantization and Artificial Neural Network. SPECOM 08, Russia. Sebastiani, F. (2002). Machine Learning in Automated Text Categorization. ACM Computing Surveys, 34(1). 1-47. Shannon, B. J. & Paliwal, K. (2005). Influences of Autocorrelation Lag Ranges on Robust Speech Recognition. Proc. IEEE Intern. Conf. on Acoustics, Speech and Signal Processing. vol. 1, 545-548 Siivola, V., Kurimo, M. & Lagus, K. (2001) Large Vocabulary Statistical Language Modeling for Continuous Speech Recognition in Finnish. Proceedings of the 7th European Conference on Speech Communication and Technology, Proc. Eurospeech. Stokes-Rees, I. (2002). A Study of the Automatic Speech Recognition Process and Speaker Adaptation. Masters Thesis. Vaishnavi, V. & Kuechler, B. (2004). Design Research in Information System. Retrieved March 26, 2005, from http://www.isworld.org/Researchdesign/drisISworld.htm Verlinde, P., Chollet, G., & Acheroy, M. (2000). Multimodal identity verification using expert fusion. InformationFusion, 1. 17-33. Xu, R. & Wunsch,D.(2005). Survey of Clustering Algorithms. IEEE Transaction on Neural Network. vol 16, no.3. Zhang, Z. (2002). A Study on Increasing Robustness against Speaker and Noise Variations in Speech Recognition. A Dissertation Submitted to Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Japan. Zhao, J., Kuang, J. & Xie, X. (2003). The Formant Structure based Feature Parameter for Speech Recognition. IEEE Workshop on Statistical Signal Processing 2003. 605-608. Zissman, M. (1996). Comparison of four approaches to automatic language identification of telephone speech. IEEE Transaction on Speech and Audio Processing,4(1).31-44. Zweig, & Campbell (1993). ROC plots: a fundamental evaluation tool in clinical medicine. Clinical Chemistry, 39 (8). 561-577. |