Asymptotically exact noise-corrupted speech likelihoods
نویسندگان
چکیده
Model compensation techniques for noise-robust speech recognition approximate the corrupted speech distribution. This paper introduces a sampling method that, given speech and noise distributions and a mismatch function, in the limit calculates the corrupted speech likelihood exactly. Though it is too slow to compensate a speech recognition system, it enables a more fine-grained assessment of compensation techniques, based on the KL divergence of individual components. This makes it possible to evaluate the impact of approximations that compensation schemes make, such as the form of the mismatch function.
منابع مشابه
Importance sampling to compute likelihoods of noise-corrupted speech
One way of making speech recognisers more robust to noise is model compensation. Rather than enhancing the incoming observations, model compensation techniques modify a recogniser’s state-conditional distributions so they model the speech in the target environment. Because the interaction between speech and noise is non-linear, even for Gaussian speech and noise the corrupted speech distributio...
متن کاملStatistical Models for Noise-Robust Speech Recognition
A standard way of improving the robustness of speech recognition systems to noise is model compensation. is replaces a speech recogniser’s distributions over clean speech by ones over noise-corrupted speech. For each clean speech component,model compensation techniques usually approximate the corrupted speech distribution with a diagonal-covariance Gaussian distribution. is thesis looks into im...
متن کاملTransforming features to compensate speech recogniser models for noise
To make speech recognisers robust to noise, either the features or the models can be compensated. Feature enhancement is often fast; model compensation is often more accurate, because it predicts the corrupted speech distribution. It is therefore able, for example, to take uncertainty about the clean speech into account. This paper re-analyses the recently-proposed predictive linear transformat...
متن کاملMissing data techniques: Feature reconstruction
Automatic speech recognition (ASR) performance degrades rapidly when speech is corrupted with increasing levels of noise. Missing data techniques (MDT) constitute a family of methods that tackle noise robust speech recognition based on the so called missing data assumption proposed in [1]. MDTs assume that (i) the noisy speech signal can be divided in speech-dominated (reliable) and noise-domin...
متن کاملSpeech Enhancement Through an Optimized Subspace Division Technique
The speech enhancement techniques are often employed to improve the quality and intelligibility of the noisy speech signals. This paper discusses a novel technique for speech enhancement which is based on Singular Value Decomposition. This implementation utilizes a Genetic Algorithm based optimization method for reducing the effects of environmental noises from the singular vectors as well as t...
متن کامل