Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition

Weninger, Felix; Watanabe, Shinji; Tachioka, Yuuki; Schuller, Björn

doi:10.1109/icassp.2014.6854478

Cited by 69 publications

(36 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, Weninger et al proposed a method for combining spectral subtraction with reverberation time estimation-based dereverberation and DAE [56]. They used reverberant and dereverberant speech to train the deep recurrent denoising autoencoder.…”

Section: Discussionmentioning

confidence: 99%

Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification

Zhang

Wang

Kai

et al. 2015

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Deep neural network (DNN)-based approaches have been shown to be effective in many automatic speech recognition systems. However, few works have focused on DNNs for distant-talking speaker recognition. In this study, a bottleneck feature derived from a DNN and a cepstral domain denoising autoencoder (DAE)-based dereverberation are presented for distant-talking speaker identification, and a combination of these two approaches is proposed. For the DNN-based bottleneck feature, we noted that DNNs can transform the reverberant speech feature to a new feature space with greater discriminative classification ability for distant-talking speaker recognition. Conversely, cepstral domain DAE-based dereverberation tries to suppress the reverberation by mapping the cepstrum of reverberant speech to that of clean speech with the expectation of improving the performance of distant-talking speaker recognition. Since the DNN-based discriminant bottleneck feature and DAE-based dereverberation have a strong complementary nature, the combination of these two methods is expected to be very effective for distant-talking speaker identification. A speaker identification experiment was performed on a distant-talking speech set, with reverberant environments differing from the training environments. In suppressing late reverberation, our method outperformed some state-of-the-art dereverberation approaches such as the multichannel least mean squares (MCLMS). Compared with the MCLMS, we obtained a reduction in relative error rates of 21.4% for the bottleneck feature and 47.0% for the autoencoder feature. Moreover, the combination of likelihoods of the DNN-based bottleneck feature and DAE-based dereverberation further improved the performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification

Zhang

Wang

Kai

et al. 2015

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

show abstract

“…Deep neural networks (DNNs) with pre-training have been shown to achieve better performance than the conventional MLP without pre-training [22]. There are many DNN, recurrent neural network (RNN) and long short-term memory (LSTM) [23][24][25][26][27][28][29] based speech enhancement and feature enhancement approaches that have been proposed for speech enhancement for human listening and robust speech recognition and that have shown good performance for the REVERB challenge task [40]. Recently, the denoising autoencoder (DAE), one type of DNN, has been shown to be effective in many noise reduction applications because higher-level representations and increased flexibility of the feature mapping function can be learned [30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

“…However, the results of DAE with small reverberation are not good compared to other methods. Typically, in the training of a DAE [26,34,35], data incorporating various environmental conditions are used.…”

Section: Introductionmentioning

confidence: 99%

Environment-dependent denoising autoencoder for distant-talking speech recognition

Ueda

Wang

Kai

et al. 2015

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

In this paper, we propose an environment-dependent denoising autoencoder (DAE) and automatic environment identification based on a deep neural network (DNN) with blind reverberation estimation for robust distant-talking speech recognition. Recently, DAEs have been shown to be effective in many noise reduction and reverberation suppression applications because higher-level representations and increased flexibility of the feature mapping function can be learned. However, a DAE is not adequate in mismatched training and test environments. In a conventional DAE, parameters are trained using pairs of reverberant speech and clean speech under various acoustic conditions (that is, an environment-independent DAE). To address the above problem, we propose two environment-dependent DAEs to reduce the influence of mismatches between training and test environments. In the first approach, we train various DAEs using speech from different acoustic environments, and the DAE for the condition that best matches the test condition is automatically selected (that is, a two-step environment-dependent DAE). To improve environment identification performance, we propose a DNN that uses both reverberant speech and estimated reverberation. In the second approach, we add estimated reverberation features to the input of the DAE (that is, a one-step environment-dependent DAE or a reverberation-aware DAE). The proposed method is evaluated using speech in simulated and real reverberant environments. Experimental results show that the environment-dependent DAE outperforms the environment-independent one in both simulated and real reverberant environments. For two-step environment-dependent DAE, the performance of environment identification based on the proposed DNN approach is also better than that of the conventional DNN approach, in which only reverberant speech is used and reverberation is not blindly estimated. And, the one-step environment-dependent DAE significantly outperforms the two-step environment-dependent DAE.

show abstract

“…Acoustic models were retrained using the reconstructed features. Weninger et al [27,28] have shown that deep recurrent neural networks (RNNs) are also suitable for feature enhancement of reverberant speech signals. Recently, Mimura et al [29] augmented the input of the autoencoder based on long shortterm memory (LSTM) [30] with phone-class information (denoted as pLSTM).…”

Section: Introductionmentioning

confidence: 99%

Joint training of DNNs by incorporating an explicit dereverberation structure for distant speech recognition

Gao

et al. 2016

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

We explore joint training strategies of DNNs for simultaneous dereverberation and acoustic modeling to improve the performance of distant speech recognition. There are two key contributions. First, a new DNN structure incorporating both dereverberated and original reverberant features is shown to effectively improve recognition accuracy over the conventional one using only dereverberated features as the input. Second, in most of the simulated reverberant environments for training data collection and DNN-based dereverberation, the resource data and learning targets are high-quality clean speech. With our joint training strategy, we can relax this constraint by using large-scale diversified real close-talking data as the targets which are easy to be collected via many speech-enabled applications from mobile internet users, and find the scenario even more effective. Our experiments on a Mandarin speech recognition task with 2000-h training data show that the proposed framework achieves relative word error rate reductions of 9.7 and 8.6 % over the multi-condition training systems for the cases of single-channel and multi-channel with beamforming, respectively. Furthermore, significant gains are consistently observed over the pre-processing approach using simply DNN-based dereverberation.

show abstract

Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition

Cited by 69 publications

References 22 publications

Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification

Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification

Environment-dependent denoising autoencoder for distant-talking speech recognition

Joint training of DNNs by incorporating an explicit dereverberation structure for distant speech recognition

Contact Info

Product

Resources

About