2001 · 84 citations · 6 references
ComputingComputer ScienceMachine LearningReal-time SystemsStatistical LearningNoiseNoise ReductionPattern RecognitionSpeech RecognitionSpeech Recognition TestingAdditive NoiseAutomatic RecognitionFramesNoise RobustnessSentence Recognition In Noise
In this paper we apply a model-based compensation method to cancel the effect of the additive noise in Automatic Speech Recognition systems. The method is formulated in a statistical framework in order to perform the optimal compensation of the noise effect given the observed noisy speech, a model describing the statistics of the speech recorded in a clean reference environment and the estimation of the noise in the noisy recognition environment. The noise is estimated using the first frames of the sentence to be recognized and a frame-by-frame noise compensation algorithm is performed, so that the compensation procedure does not constrain real-time speech recognition systems and is compatible with emerging technologies based on distributed speech recognition.
6
Speech recognition in noisy environments: A survey
Yifan Gong · Speech Communication · 1995 · 638 citations
Speech recognition in noisy environments
Pedro J. Moreno · 1996 · 290 citations
HMM recognition in noise using parallel model combination
Mark Gales, Steve Young · 1993 · 96 citations