Levent M. Arslan
Bogazici University Department of Electrical and Electronics Engineering

Areas of interest:

 

  
Courses Taught this semester

Freely Available software

Speech Enhancement Demo on Ataturk's Voice

Turkish Text-to-Speech System Output

There is no intonation model yet. This is the first prototype example.
Email
arslanle@boun.edu.tr

Postal Mail
Bogazici University
Electrical and Electronics Engineering Department
Bebek, 80815, Istanbul, TURKEY

Phone
Office: +90 (212) 263 15 40 (ext. 1421)
Cellular: +90 (532) 446 48 51

FAX
+90 (212) 287 24 65

Education

High School Diploma, Ankara Fen Lisesi., Turkey, 1986
B.S. in Electrical Engineering, Bogazici University., Turkey, 1991
Senior Project: "Edge Detection Using Linear Prediction Methods"
M.S. in Electrical Engineering, Duke University, USA, 1993.
M.S. Thesis title: "Markov Model Based Phoneme Class Partitioning for Improved Iterative Speech Enhancement"
Ph.D. in Electrical Engineering, Duke University, USA, 1996.
Ph.D. Thesis title: "Foreign Accent Classification in American English"

Journal Publications

L.M. Arslan and D. Talkin Codebook Based Face Point Trajectory Synthesis Algorithm using Speech Input
Speech Communication Journal , vol.27, No.2, pp. 81-93, March 1999.
L.M. Arslan and J.H.L. Hansen Selective Training for Hidden Markov Models
IEEE Trans. on Speech and Audio Processing , vol.7, No.1, pp. 46-55, January 1999.
L.M. Arslan and J.H.L. Hansen Likelihood Decision Boundary Estimation Between HMM Pairs in Speech Recognition
IEEE Trans. on Speech and Audio Processing , vol. 6, no. 4, July 1998.
L.M. Arslan and J.H.L. Hansen A Study of Temporal Features and Frequency Characteristics in American English Foreign Accent
Journal of Acoust. Soc. of America, vol.102, No.1, pp. 28-40, July 1997
(appeared as featured article).
L.M. Arslan and J.H.L. Hansen Speech Enhancement for Cross-Talk Interference
IEEE Signal Processing Letters, vol.4, No.4, pp. 92-95, April 1997.
L.M. Arslan and J.H.L. Hansen Language Accent Classification in American English
Speech Communication Journal, vol.18, No.4, pp. 353-367, August 1996.
J.H.L. Hansen and L.M. Arslan Robust Feature-Estimation and Objective Quality Assessment for Noisy Speech Recognition using the Credit Card Corpus,
IEEE Trans. on Speech and Audio Processing, vol.3, No.3, pp. 169-184, May 1995.
J.H.L. Hansen and L.M. Arslan Markov Model Based Phoneme Class Partitioning for Improved Constrained Iterative Speech Enhancement
IEEE Trans. on Speech and Audio Processing, vol.3, No.1, pp. 98-104, January 1995.
L.M. Arslan Speaker Transformation Algorithm using Segmental Codebooks (STASC)
accepted to Speech Communication Journal , (February 1999).

Peer Reviewed Conference Publications

L.M. Arslan and D. Talkin Speech Driven 3-D Face Point Trajectory Synthesis Algorithm
ICSLP Proceedings, Sydney, Australia, November 1998.
L.M. Arslan and D. Talkin 3-D Face Point Trajectory Synthesis using an Automatically derived Visual Phoneme Similarity matrix
AVSP Proceedings, Terrigal, Australia, December 1998.
F. Galanes, J. Unverferth, L.M. Arslan and D. Talkin Generation of lip-synched synthetic faces from phonetically clustered face movement data
AVSP Proceedings, Terrigal, Australia, December 1998.
L.M. Arslan and D. Talkin Speaker Transformation using Sentence HMM Based Alignments and Detailed Prosody Modification
IEEE Proc. ICASSP, Seattle, USA, May 1998.
L.M. Arslan and D. Talkin Voice Conversion by Codebook Mapping of Line Spectral Frequencies and Excitation Spectrum
EUROSPEECH Proceedings, Rhodes, Greece, September 1997.
L.M. Arslan and J.H.L. Hansen A Study of Frequency Characteristics in Foreign Accent
IEEE Proc. ICASSP, Munich, Germany, April 1997.
L.M. Arslan and J.H.L. Hansen Improved HMM Training and Scoring Strategies with Application to Accent Classification
IEEE Proc. ICASSP, vol.2, pp. 589-592, Atlanta, USA, May 1996 .
L.M. Arslan and J.H.L. Hansen New Methods for Adaptive Noise Suppression
IEEE Proc. ICASSP vol.1, pp. 812-815, Detroit, USA, May 1995.
L.M. Arslan and J.H.L. Hansen Foreign Accent Classification using Source Generator Based Prosodic Features
IEEE Proc. ICASSP vol.1, pp. 836-839, Detroit, USA, May 1995.
L.M. Arslan and J.H.L. Hansen A Minimum Cost Based Phoneme Class Detector for Improved Iterative Speech Enhancement
IEEE Proc. ICASSP vol.2, pp. 045-048, Adelaide, Australia, April 1994.
J.H.L. Hansen, B. Womack and L.M. Arslan A Source Generator Based Production Model for Environmental Robustness in Speech Recognition
ICSLP Proceedings, vol.3, pp. 1003-1006, Yokohama, Japan, September 1994.

Patents

Adaptive Weiner filtering using a dynamic suppression factor
L.M. Arslan, A. Mccree, and V. Viswanathan. Issued Jan 6, 1998. US Patent No: 5706395.
Speaker-Dependent Garbage Models for Out of Vocabulary Word Rejection
L.M. Arslan, L. Netsch, and Raja Rajasekaran. Filed 1998.
Voice Conversion by Segmental Codebook Mapping of Line Spectral Frequencies and Excitation
L.M. Arslan, and D. Talkin. Filed 1997.
3-D Face Point Trajectory Synthesis
L.M. Arslan, and D. Talkin. Filed 1998.

Industrial Experience:

Awards and Honors

Hobbies

For more information please send e-mail to arslanle@boun.edu.tr,