• Publications
  • Influence
Spoken Language Processing: A Guide to Theory, Algorithm and System Development
From the Publisher: New advances in spoken language processing: theory and practice In-depth coverage of speech processing, speech recognition, speech synthesis, spoken language understanding,Expand
  • 1,779
  • 204
  • PDF
Learning deep structured semantic models for web search using clickthrough data
Latent semantic models, such as LSA, intend to map a query to its relevant documents at the semantic level where keyword-based matching often fails. In this study we strive to develop a series of newExpand
  • 1,018
  • 185
  • PDF
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe aExpand
  • 2,367
  • 131
  • PDF
Spoken Language Processing
A filling assembly for vacuum filling impervious open mouth paper bags with finely divided particulate material. A filling head is provided with at least two independent vertically extending chambersExpand
  • 919
  • 71
Hidden conditional random fields for phone classification
In this paper, we show the novel application of hidden conditional random fields (HCRFs) – conditional random fields with hidden state sequences – for modeling speech. Hidden state sequences areExpand
  • 354
  • 36
  • PDF
HMM adaptation using vector taylor series for noisy speech recognition
In this paper we address the problem of robustness of speech recognition systems in noisy environments. The goal is to estimate the parameters of a HMM that is matched to a noisy environment, given aExpand
  • 314
  • 33
  • PDF
Evaluation of the SPLICE algorithm on the Aurora2 database
This paper describes recent improvements to SPLICE, Stereo-based Piecewise Linear Compensation for Environments, which produces an estimate of cepstrum of undistorted speech given the observedExpand
  • 155
  • 26
  • PDF
Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion
This paper presents a new technique for dynamic, frame-by-frame compensation of the Gaussian variances in the hidden Markov model (HMM), exploiting the feature variance or uncertainty estimatedExpand
  • 172
  • 24
  • PDF
Adaptation of maximum entropy capitalizer: Little data can help a lot
Abstract A novel technique for maximum “a posteriori” (MAP) adaptation of maximum entropy (MaxEnt) and maximum entropy Markov models (MEMM) is presented. The technique is applied to the problem ofExpand
  • 240
  • 23
  • PDF
A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions
In this paper, we present our recent development of a model-domain environment robust adaptation algorithm, which demonstrates high performance in the standard Aurora 2 speech recognition task. TheExpand
  • 107
  • 20
  • PDF