Stephen M. Chu

Stephen M. Chu

Auto-generated profile, based on publicly available information

Stephen M. Chu

IBM T.J. Watson Research Center

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2007 in Language Resources and Evaluation
Verified
Journal Article
Closed access
PDF file
DMDjamel Mostefa
Djamel Mostefa
NMNicolas Moreau
Nicolas Moreau
KCKhalid Choukri
Khalid Choukri
GPGerasimos Potamianos
Gerasimos Potamianos
SCStephen M. Chu
Stephen M. Chu
CRCedrick Rochet
Cedrick Rochet

1 April 2007
Verified
Conference Paper
Closed access
SCStephen M. Chu
Stephen M. Chu
HKHong-Kwang Kuo
Hong-Kwang Kuo
YLYi Y Liu
Yi Y Liu
YQYong Qin
Yong Qin
QSQin Shi
Qin Shi
GZGeoffrey Zweig
Geoffrey Zweig
This paper describes the technical and system building advances in the automatic transcription of Mandarin broadcast speech made at IBM in the first year of the DARPA GALE program. In particular, we discuss the application of minimum phone error (MPE) discriminative training and a new topic-adaptive language modeling technique. We present results on both the RT04 evaluation data and two larger community-defined test sets designed to cover both the broadcast news and the broadcast conversation domain. It is shown that with the described advances, the new transcription system achieves a 26.3% relative reduction in character error rate over our previous best-performing system, and is competitive with published numbers on these datasets.

25 March 2014
Verified
Book Chapter
Closed access
PDF file
HSHagen Soltau
Hagen Soltau
GSGeorge Saon
George Saon
LMLidia Mangu
Lidia Mangu
HKHong-Kwang Kuo
Hong-Kwang Kuo
BKBrian Kingsbury
Brian Kingsbury
FBFadi Biadsy
Fadi Biadsy

1 June 2007
Verified
Conference Paper
Closed access
SCStephen M. Chu
Stephen M. Chu
THThomas S. Huang
Thomas S. Huang
The fusion of audio and visual speech is an instance of the general sensory fusion problem. The sensory fusion problem arises in the situation when multiple channels carry complementary information about different components of a system. In the case of audio-visual speech, the two modalities manifest two aspects of the same underlying speech production process. From an observer's view, the audio channel and the visual channel represent two interacting stochastic processes. We seek a framework that can model the two individual processes as well as their dynamic interactions. One interesting aspect of audio-visual speech is the inherent asynchrony between the audio and visual channels. Most early integration approaches to the fusion problem assume tight synchrony between the two. However, studies have shown that human perception of bimodal speech does not require rigid synchronization of the two modalities. Furthermore, humans appear to use the audio-visual asynchronies as multimodal features. For example, it is well known that the voice onset time is an important cue to the voicing feature in stop consonants. This information can be conveyed bimodally by the interval between seeing the stop release and hearing the vocal cord vibration. Therefore, a successful fusion scheme should not only be tolerant to asynchrony between the audio and visual cues, but also be apt to capture and exploit this bimodal feature.

1 July 2006
Verified
Conference Paper
Closed access
ZZZhenqiu Zhangy
Zhenqiu Zhangy
GPGerasimos Potamianos
Gerasimos Potamianos
SCStephen M. Chu
Stephen M. Chu
JTJilin Tu
Jilin Tu
THThomas S. Huang
Thomas S. Huang
We present a robust vision system for single person tracking inside a smart room using multiple synchronized, calibrated, stationary cameras. The system consists of two main components, namely initialization and tracking, assisted by an additional component that detects tracking drift. The main novelty lies in the adaptive tracking mechanism that is based on subspace learning of the tracked person appearance in selected two-dimensional camera views. The sub-space is learned on the fly, during tracking, but in contrast to the traditional literature approach, an additional "forgetting" mechanism is introduced, as a means to reduce drifting. The proposed algorithm replaces mean-shift tracking, previously employed in our work. By combining the proposed technique with a robust initialization component that is based on face detection and spatio-temporal dynamic programming, the resulting vision system significantly outperforms previously reported systems for the task of tracking the seminar presenter in data collected as part of the CHIL project

22 February 2015 in arXiv
Verified
Preprint
Open access
PDF file
JYJunchi Yan
Junchi Yan
MGMin Gong
Min Gong
CSChanghua Sun
Changhua Sun
JHJin Huang
Jin Huang
SCStephen M. Chu
Stephen M. Chu
Sales pipeline analysis is fundamental to proactive management of an enterprize's sales pipeline and critical for business success. In particular, win propensity prediction, which involves quantitatively estimating the likelihood that on-going sales opportunities will be won within a specified time window, is a fundamental building block for sales management and lays the foundation for many applications such as resource optimization and sales gap analysis. With the proliferation of big data, the use of data-driven predictive models as a means to drive better sales performance is increasingly widespread, both in business-to-client (B2C) and business-to-business (B2B) markets. However, the relatively small number of B2B transactions (compared with the volume of B2C transactions), noisy data, and the fast-changing market environment pose challenges to effective predictive modeling. This paper proposes a machine learning-based unified framework for sales opportunity win propensity prediction, aimed at addressing these challenges. We demonstrate the efficacy of our proposed system using data from a top-500 enterprize in the business-to-business market.