Uncertainty measures for improving exemplar-based source separation

In this paper two models for channel estimation in exemplar-based noise robust speech recognition are proposed. Building on a compositional model that models noisy speech and a combination of noise and speech atoms, the first model iteratively estimates a filter to best compensate the mismatch with the observed noisy speech. The second model estimates separate filters for the noise and speech atoms. We show that both models enable noise-robust ASR even if the channel characteristics of the noisy speech do not match those of the exemplars in the dictionary. Moreover, the second model, which is able to estimate separate filters for speech and noise, is shown to be robust even in the presence of bandwidth-limited sources.

show abstract

Exemplar-based joint channel and noise compensation

Gemmeke

Virtanen

Demuynck

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

show abstract

Estimating Uncertainty to Improve Exemplar-Based Feature Enhancement for Noise Robust Speech Recognition

Kallasjoki

Gemmeke

Palomäki

2014

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Memory-Enhanced Neural Networks and NMF for Robust ASR

Geiger

Weninger

Gemmeke

et al. 2014

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

In this article we address the problem of distant speech recognition for reverberant noisy environments. Speech enhancement methods, e. g., using non-negative matrix factorization (NMF), are succesful in improving the robustness of ASR systems. Furthermore, discriminative training and feature transformations are employed to increase the robustness of traditional systems using Gaussian mixture models (GMM). On the other hand, acoustic models based on deep neural networks (DNN) were recently shown to outperform GMMs. In this work, we combine a state-of-the art GMM system with a deep Long Short-Term Memory (LSTM) recurrent neural network in a double-stream architecture. Such networks use memory cells in the hidden units, enabling them to learn long-range temporal context, and thus increasing the robustness against noise and reverberation. The network is trained to predict frame-wise phoneme estimates, which are converted into observation likelihoods to be used as an acoustic model. It is of particular interest whether the LSTM system is capable of improving a robust state-of-the-art GMM system, which is conrmed in the experimental results. In addition, we investigate the efciency of NMF for speech enhancement on the front-end side. Experiments are conducted on the medium-vocabulary task of the 2nd CHiME Speech Separation and Recognition Challenge, which includes reverberation and highly variable noise. Experimental results show that the average word error rate of the challenge baseline is reduced by 64% relative. The best challenge entry, a noise-robust state-of-the-art recognition system, is outperformed by 25% relative.

show abstract

Uncertainty measures for improving exemplar-based source separation

Cited by 4 publications

References 7 publications

Exemplar-based joint channel and noise compensation

Exemplar-based joint channel and noise compensation

Estimating Uncertainty to Improve Exemplar-Based Feature Enhancement for Noise Robust Speech Recognition

Memory-Enhanced Neural Networks and NMF for Robust ASR

Contact Info

Product

Resources

About