• Publications
  • Influence
Robust automatic speech recognition with missing and unreliable acoustic data
TLDR
This paper describes an approach to robust ASR which acknowledges the fact that some spectro-temporal regions will be dominated by noise. Expand
  • 684
  • 72
  • PDF
The PASCAL CHiME speech separation and recognition challenge
TLDR
This paper describes a speech recognition evaluation that was designed to model the essential difficulties of the multisource environment problem while remaining on a scale that would make it accessible to a wide audience. Expand
  • 238
  • 28
  • PDF
Soft decisions in missing data techniques for robust automatic speech recognition
TLDR
In previous work we have developed the theory and demonstrated the promise of the Missing Data approach to robust Automatic Speech Recognition. Expand
  • 166
  • 14
  • PDF
The CHiME corpus: a resource and a challenge for computational hearing in multisource environments
TLDR
We present a new corpus designed for noise-robust speech processing research, CHiME. Expand
  • 128
  • 14
  • PDF
From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition
TLDR
We introduce two absolute CSR performance measures: MER (match error rate) and WIL (word information lost). Expand
  • 60
  • 13
  • PDF
Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise
TLDR
In this study, techniques for classification with missing or unreliable data are applied to the problem of noise-robustness in Automatic Speech Recognition (ASR). Expand
  • 123
  • 11
  • PDF
Handling missing data in speech recognition
  • 95
  • 9
Some solution to the missing feature problem in data classification, with application to noise robust ASR
TLDR
We address the theoretical and practical issues involved in automatic speech recognition (ASR) when some of the observation data for the target signal is masked by other signals. Expand
  • 100
  • 9
  • PDF
Missing data techniques for robust speech recognition
TLDR
In noisy listening conditions, the information available on which to base speech recognition decisions is necessarily incomplete: some spectro-temporal regions are dominated by other sources. Expand
  • 115
  • 8
  • PDF
A silent speech system based on permanent magnet articulography and direct synthesis
TLDR
This paper introduces a 'Silent Speech Interface' with the potential to restore the power of speech to people who have completely lost their voices. Expand
  • 32
  • 5
  • PDF