Weizhong Zhu  Weizhong Zhu photo       

contact information

Speech Scientist
Thomas J. Watson Research Center, Yorktown Heights, NY USA
  +1dash914dash945dash1328

links

Professional Associations

Professional Associations:  IEEE  |  IEEE Signal Processing Society


2017

Speaker Diarization: A Perspective on Challenges and Opportunities from Theory to Practice
K. Church, W. Zhu, J. Vopicka, J. Pelecanos, D. Dimitriadis and P. Fousek
IEEE ICASSP, 2017


2016

Online Speaker Diarization using Adapted i-Vector Transforms
W. Zhu and J. Pelecanos
IEEE ICASSP, 2016

C2D2E2: Using Call Centers to Motivate the Use of Dialog and Diarization in Entity Extraction
K. Church, W. Zhu and J. Pelecanos
EMNLP workshop, 2016


2015

Nearest Neighbor based i-Vector Normalization for Robust Speaker Recognition under Unseen Channel Conditions
W. Zhu, S. Sadjadi and J. Pelecanos
IEEE ICASSP, 2015


2014

SVM based Speaker Recognition: Harnessing Trials with Multiple Enrollment Sessions
J. Pelecanos, W. Zhu and S. Yaman
Interspeech, 2014

Nearest Neighbor Discriminant Analysis for Robust Speaker Recognition
S. Sadjadi, J. Pelecanos and W. Zhu
Interspeech, 2014


2013

The IBM RATS Phase II speaker recognition system: Overview and analysis
W Zhu, S Yaman, J Pelecanos
ISCA Interspeech, 2013

Unifying PLDA and Polynomial Kernel SVMs
S. Yaman, J. Pelecanos and W. Zhu
IEEE ICASSP, 2013


2011

Forensically inspired approaches to automatic speaker recognition
Kyu J Han, Mohamed Kamal Omar, J Pelecanos, Cezar Pendus, Sibel Yaman, Weizhong Zhu
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 5160--5163


2008

Handheld speech to speech translation system
Yuqing Gao, Bowen Zhou, Weizhong Zhu, Wei Zhang
Automatic Speech Recognition on Mobile Devices and over Communication Networks, 327--346, Springer, 2008


2006

IBM MASTOR SYSTEM: Multilingual automatic speech-to-speech translator
Yuqing Gao, Liang Gu, Bowen Zhou, Ruhi Sarikaya, Mohamed Afify, Hong-Kwang Kuo, Wei-zhong Zhu, Yonggang Deng, Charles Prosser, Wei Zhang, others
Proceedings of the Workshop on Medical Speech Translation, pp. 53--56, Association for Computational Linguistics, 2006
Abstract

Recent advances of IBM’s handheld speech translation system
Weizhong Zhu, Bowen Zhou, Charles Prosser, Pavel Krbec, Yuqing Gao
Proceedings of Interspeech, 1181--1184, 2006

INTERSPEECH 2006-ICSLP Ninth International Conference on Spoken Language Processing
Weizhong Zhu, Bowen Zhou, Charles Prosser, Pavel Krbec, Yuqing Gao
2006


2005

Log-energy dynamic range normalization for robust speech recognition
Weizhong Zhu, Douglas O’Shaughnessy
proc. ICASSP1, 245--248, 2005


2004

Incorporating frequency masking filtering in a standard MFCC feature extraction algorithm
Weizhong Zhu, Douglas O'Shaughnessy
Signal Processing, 2004. Proceedings. ICSP'04. 2004 7th International Conference on, pp. 617--620


2003

IMPROVE ASR PERFORMANCE IN NOISY CONDITIONS
Weizhong Zhu, Douglas O'Shaughnessy
Proceedings, 357, IEEE, 2003

Using noise reduction and spectral emphasis techniques to improve ASR performance in noisy conditions
Weizhong Zhu, Douglas O'Shaughnessy
Automatic Speech Recognition and Understanding, 2003. ASRU'03. 2003 IEEE Workshop on, pp. 357--362


2000

Study of talker individuality by using ARX speech analysis-synthesis-editing system
Weizhong Zhu, Kenji Matsui, Hideki Kasuya
Acoustics, Speech, and Signal Processing, 2000. ICASSP'00. Proceedings. 2000 IEEE International Conference on, pp. 1331--1334

Tracking Behavior of the Kalman Filter Algorithm for ARX Parameter Estimation.
W ZHU
Reports of the Meeting. the Acoustical Society of Japan2000, 223--224

A study of phoneme and syllable duration characteristics of Mandarin Chinese
Weizhong Zhu, Kenji Matsui
Proc. International Symposium on Chinese Spoken Language Processing, 2000


1998

ARX 音声生成モデルに基づいた音声分析・合成・編集システム
Weizhong Zhu, Hideki Kasuya
Journal of the Acoustical Society of Japan (E) 19(3), 223--230, 社団法人日本音響学会, 1998

A speech analysis-synthesis-editing system based on the ARX speech production model
Weizhong Zhu, Hideki Kasuya
Journal of the Acoustical Society of Japan (E) 19(3), 223--230, Journal@rchive, 1998


1997

Roles of static and dynamic features of formant trajectories in the perception of talk indedivduality.
Weizhong Zhu, Hideki Kasuya
EUROSPEECH, 1997


1996

Voice quality conversion based on an ARX speech analysis--synthesis method and its application to the study of speaker individuality
Hideki Kasuya, Weizhong Zhu, Masahiro Matsuda, Chang-Sheng Yang
The Journal of the Acoustical Society of America100, 2600, 1996

A new speech synthesis system based on the ARX speech production model
Weizhong Zhu, Hideki Kasuya
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on, pp. 1413--1416


1994

An integrated acoustic evaluation system of pathologic voice
Weizhong Zhu, Yoshinobu Kikuchi, Yasuo Endo, Hideki Kasuya, Minoru Hirano, Masanao Ohashi
Third International Conference on Spoken Language Processing, 1994