De-reverberation using DNN for Non-Reference Reverberant Speech Intelligibility Estimation

Nakazawa, Kazushi; Kondo, Kazuhiro

doi:10.1109/gcce.2018.8574754

Cited by 4 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reverberation is also a kind of noise, produced by the source itself [1]. It is also diffuse in nature [178] and so acts as a diffuse noise source.…”

Section: B Musicmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net

Gul,

Khan

2023

IEEE Access

View full text Add to dashboard Cite

The recent surge in the use of Deep Neural Networks (DNNs) has also made its mark in the field of Audio Enhancement (AE), providing much better quality than the classical methods. Although, there are dedicated audio processing DNNs, yet, many recent models of AE have utilized U-Net: a DNN based on Convolutional Neural Network (CNN), fundamentally developed for image segmentation. It is found that the useful features hidden in the time domain are highlighted when the audio signal is converted to a spectrogram, which can be treated as an image. In this article, we will review the recent work, utilizing U-Nets for different AE applications. Different than other published reviews, this review focuses entirely on AE techniques based on image U-Nets. We will discuss the need for AE, U-Net comparison to other DNNs, the benefits of converting the audio to 2D, input representations that are useful for different AE applications, the architecture of vanilla U-Net and the pre-trained models, variations in vanilla architecture incorporated in different E models, and the state-of-the-art AE algorithms based on U-Net in various applications. Apart from speech and music, this article discusses a wide range of audio signals e.g. environmental, biomedical, bioacoustics, and industrial sounds, not covered collectively in a single article in previously published studies. The article ends with the discussion of colored spectrograms in future AE applications.INDEX TERMS CNNs; image processing deep neural networks; pre-trained networks; spectrogram.;U-Net.

show abstract

“…Reverberation is also a kind of noise, produced by the source itself [1]. It is also diffuse in nature [178] and so acts as a diffuse noise source.…”

Section: B Musicmentioning

confidence: 99%

“…Audio Enhancement (AE) is the process of improving the audio quality by removing the noise (produced by the surrounding sources or from the same source in the form of echoes) and filling the gaps due to damage or intrusions [1]. Whether the audio is generated by the objects surrounding us (e.g.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net

Gul,

Khan

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…With the development of Neural Networks (NNs), there has been tremendous improvement in a variety of speech recognition and acoustic signal processing tasks [16]. The binaural dereverberation models in [8], [16] and [17] uses artificial neural network (ANN) for binaural dereverberation preprocessing, the model in [18] uses the recurrent neural network (RNN) and interaural cues for speech enhancement in reverberant noisy conditions, while the models in [19] and [20] use the U-Net (a deep convolutional neural network (CNN)) for dereverberation, but these are monaural models.…”

Section: Introductionmentioning

confidence: 99%

Preserving the beamforming effect for spatial cue-based pseudo-binaural dereverberation of a single source

Gul

Khan

Shah

2023

Computer Speech & Language

View full text Add to dashboard Cite

“…Another intelligibility estimation approach is the non-reference type of estimation, which does not use a reference signal [14,15] . We believe that such approaches have high practicality because the intelligibility can be determined using only the broadcast speech.…”

Section: Introductionmentioning

confidence: 99%

“…To overcome these, various factors must be optimized. In particular, in previous research [15], we performed the evaluation considering the intelligibility of reverberant speech; however, we did not comprehensively evaluate a wide range of reverberation and noise combinations. The present study provides the basic analysis results necessary to improve the method for the estimation of nonreference type intelligibility.…”

Section: Introductionmentioning

confidence: 99%

Japanese speech intelligibility estimation and prediction using objective intelligibility indices under noisy and reverberant conditions

Kobayashi

Kondo

2019

Applied Acoustics

Self Cite

View full text Add to dashboard Cite

De-reverberation using DNN for Non-Reference Reverberant Speech Intelligibility Estimation

Cited by 4 publications

References 1 publication

A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net

A Survey of Audio Enhancement Algorithms for Music, Speech, Bioacoustics, Biomedical, Industrial, and Environmental Sounds by Image U-Net

Preserving the beamforming effect for spatial cue-based pseudo-binaural dereverberation of a single source

Japanese speech intelligibility estimation and prediction using objective intelligibility indices under noisy and reverberant conditions

Contact Info

Product

Resources

About