Levent M. Arslan
Bogazici University Department of Electrical and Electronics Engineering
Areas of interest:
- Digital Signal
Processing
- Automatic Speech
Recognition
- Speech Enhancement
- Text-to-Speech
Synthesis
- Speaker Recognition
- Voice Conversion
Courses Taught this
semester
Freely Available
software
- speech toolbox with
graphic user interface for MATLAB for speech production modeling, formant
and pitch analysis, speech enhancement, etc.
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.
Electrical and Electronics Engineering Department
Bebek, 34342, Istanbul, TURKEY
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
Speech Conversion System and Methodology
L.M. Arslan, F. Deutsch. Filed 2005.
Adaptive
Weiner filtering using line spectral frequencies
L.M. Arslan, A. Mccree, and V. Viswanathan. Texas
Instruments Inc., Issued July 17, 2001. Patent No: US 6,263,307.
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. Texas Instruments
Inc., Issued June 5, 2001. Patent No: US 6,243,677.
Voice Conversion by
Segmental Codebook Mapping of Line Spectral Frequencies and Excitation
L.M. Arslan, and D. Talkin. Microsoft Corporation, Issued September 2, 2003. Patent No: US 6,615,174.
3-D Face Point
Trajectory Synthesis
L.M. Arslan, and D. Talkin. Microsoft
Corporation, Issued September 10,
2002. Patent No: US 6,449,595.
Industrial
Experience:
·
R&D
Director: Sestek Speech Technologies Inc., Istanbul, Turkey, 2000-present
·
Technical
Consultant: Sakhr Software Co., Cairo, Egypt, 1998-2000
·
Member
of Technical Staff: Entropic Research Lab, Washington, DC, USA, 1996-1998
·
Research
Intern: Texas Instruments SISL Lab., Dallas, TX, USA, Summer 1995
·
Research
Intern: Texas Instruments SISL Lab., Dallas, TX, USA, Summer 1994
Awards
and Honors
·
Mustafa
Parlar Technology Incentive Award
·
TTGV
Thesis Advisor Award for Industrial Practice
·
Award
for technical excellence at Texas Instruments (1995)
·
Teaching
Assistant Fellowship, Duke University (1991 - 1992)
·
Research
Assistant Fellowship, Duke University (1992 - 1996)
·
Fellowship,
Sabanci Foundation, Turkey (1986 - 1991)
·
Reviewer
for IEEE Transactions on Speech and Audio Proc.
·
Reviewer
for IEEE Signal Processing Letters.
·
Reviewer
for Speech Communication Journal.
·
Reviewer
for Signal Processing Journal.
Hobbies
·
Playing
Soccer, Tennis, Voleyball
·
Painting
·
Playing
the Violin
For more information please send e-mail to arslanle@boun.edu.tr,