The MERL/MELCO/TUM system for the REVERB Challenge using Deep Recurrent Neural Network Feature Enhancement

By Felix Weninger, Shinji Watanabe, Jonathan Le Roux, John R. Hershey, Yuuki Tachioka, Jürgen T. Geiger, Björn Schuller, Gerhard Rigoll. 2014

44 citations recorded by the source corpus.

Subfields: Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

Citations in the corpus

The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments (2015, background): “…at multi-microphone front-end processing level in order to feed ASR with an enhanced speech input [4, 5, 6, 7, 8], the performance loss observed from close-talking to distant-speech remains quite critical, even when the most advanced DNN-based backend frameworks are adopted [9, 10, 11, 12, 13, 14].”
Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, methodology): “good performance in subjective quality and subjective reverberation scores [14] as well as in ASR performance [15].”
Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks (2015, methodology): “In [4], the LSTM was applied to enhance the reverberated speech.”
Realistic Multi-Microphone Data Simulation for Distant Speech Recognition (2016, background): “…[3], source separation [4], speech dereverberation [5], speaker localization [6], acoustic event detection [7] as well as acoustic modeling [8, 9, 10, 11, 12], DSR still exhibits a lack of robustness, especially when adverse acoustic conditions originated by non-stationary noises and acoustic…”
Deep Learning for Environmentally Robust Speech Recognition (2017, unknown): “s then extended to coping with reverberation in [70]–[74]. With the help of LSTM-RNN, the speech recognition systems perform much better than the ones without LSTM-RNN when decoding noisy speech [70]–[73]. 3) Based on CNN: Owing to the capability to capture the inherentrepresentationsembeddedin the ”
Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments (2014, methodology): “, in the form of beamforming [4], multichannel linear prediction [5], blocking matrix-based postfilters [6] or coherence-based postfilters [7].”
The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices (2015, background): “Top-performing systems in recent challenge programs associated with noise robustness integrate strong front-ends and state-of-the-art back-ends [1, 2, 3].”
A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research (2016, methodology): “Weninger [39] x x x x x x x”
Contaminated speech training methods for robust DNN-HMM distant speech recognition (2017, background): “Concerning the latter field, the research community is currently experiencing a revolution due to the introduction of Deep Neural Networks (DNNs) [13], which have consistently outperformed previous Gaussian Mixture Models (GMMs) for both close [14] and distant-talking scenarios [15, 16, 17, 18, 19].”
Batch-normalized joint training for DNN-based distant speech recognition (2016, background): “Nevertheless, the recent success of deep learning has not only largely contributed to the substantial improvement of the speech recognition part of a DSR system [19, 20, 21, 22, 23, 24, 25], but has also enabled the de-a r X i v : 1703 .”