Speech Dereverberation

By Patrick A. Naylor, Nikolay D. Gaubitch. 2010

494 citations recorded by the source corpus.

Subfields: Signal Processing

How researchers see this paper

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

In Signal Processing

1. Jinyu Li
2. Mirco Ravanelli
3. Dong Yu
4. Maurizio Omologo
5. Yifan Gong
6. Yoshua Bengio
7. Li Deng
8. Shinji Watanabe

Citations in the corpus

• DDSP: Differentiable Digital Signal Processing (2020, background): “Removing reverb in a “blind” setting, where only reverberated audio is available, is a standing problem in acoustics (Naylor & Gaubitch, 2010).”
• Realistic Multi-Microphone Data Simulation for Distant Speech Recognition (2016, background): “…progress in various related fields, including spatial filtering [1, 2], microphone selection [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,…”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “tion is a well-recognized challenge in speech processing, particularly when it is combined with background noise. As a result, dereverberation has been actively investigated for a long time [5] [191] [131] [61]. Han et al. [57] proposed the first DNN based approach to speech dereverberation. This ap”
• Speech Dereverberation Using Fully Convolutional Networks (2018, background): “ [1]. These are often manifested as “blurring” effects on the shorttime Fourier transform (STFT) images. A plethora of methods for speech dereverberation using both single- and multimicrophone exists [2]. The REVERB challenge [3] was a large community-wide endeavor to put together a common dataset f”
• An Overview of Noise-Robust Automatic Speech Recognition (2014, background): “This is consistent with the need to develop noise-robust ASR technologies for real-world deployment.”
• A Reverberation-Time-Aware Approach to Speech Dereverberation Based on Deep Neural Networks (2017, background): “One direct way is to estimate an inverse filter of the room impulse response (RIR) [7] to deconvolve the reverberant signal.”
• Machine learning in acoustics: Theory and applications. (2019, unknown): “268.”
• Contaminated speech training methods for robust DNN-HMM distant speech recognition (2017, background): “can be found in http://dirha.fbk.eu/. Considerable progresses were fostered by substantial advances in spatial filtering [6, 7], microphone selection [8], source separation [9], speech dereverberation [10] as well as speaker localization [11], acoustic event detection [12] and acoustic modeling. Conc”
• The reverb challenge: A common evaluation framework for dereverberation and recognition of reverberant speech (2013, unknown): “Index Terms— Reverberant speech, dereverberation, ASR, evaluation, challenge”
• A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research (2016, background): “In recent years, however, research on reverberant speech processing has achieved significant progress in both the audio processing and ASR fields [4, 5], mainly”
• On the selection of the impulse responses for distant-speech recognition based on contaminated speech training (2014, background): “Important efforts have been recently made on this topic by the scientific communities related to Automatic Speech Recognition (ASR), dereverberation and speech enhancement [1], as also witnessed by the REVERB challenge [2].”