B
Biing-Hwang Juang
Researcher at Georgia Institute of Technology
Publications - 8
Citations - 8477
Biing-Hwang Juang is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Bayes error rate & Hidden Markov model. The author has an hindex of 3, co-authored 8 publications receiving 8384 citations.
Papers
More filters
Book
Fundamentals of speech recognition
TL;DR: This book presents a meta-modelling framework for speech recognition that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of manually modeling speech.
Book ChapterDOI
Historical Perspective of the Field of ASR/NLU
TL;DR: The goal of this section is to document the history of research in speech recognition and natural language understanding, and to point out areas where great progress has been made, along with the challenges that remain to be solved in the future.
Proceedings ArticleDOI
Multi-Class Classification Using a New Sigmoid Loss Function for Minimum Classification Error (MCE)
TL;DR: A new loss function has been introduced for Minimum Classification Error, that approaches optimal Bayes' risk and also gives an improvement in performance over standard MCE systems when evaluated on the Aurora connected digits database.
Proceedings ArticleDOI
An Investigation of Non-Uniform Error Cost Function Design in Automatic Speech Recognition
Qiang Fu,Biing-Hwang Juang +1 more
TL;DR: Some viable techniques for the design of the non-uniform error cost function in the context of automatic speech recognition (ASR) according to different training scenarios are proposed.
Proceedings ArticleDOI
Feature Transformation and Model Design Using Minimum Classification Error
TL;DR: A Minimum Classification Error (MCE) based recognition system that also estimates a global feature transformation matrix has been implemented that makes the explicit assumption that the covariance matrix of the Gaussian mixtures is diagonal when estimating the transformation matrix.