Speech enhancement with weighted denoising auto-encoder

Xia, Bing-yin; Bao, Changchun

doi:10.21437/interspeech.2013-754

Cited by 36 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, instead of explicitly modeling the babble noise, we focus on learning a 'mapping' between noisy speech spectra and clean speech spectra, inspired by recent works on speech enhancement using neural networks [8,9,10,11]. However, the model size of Neural Networks easily exceeds several hundreds of megabytes, limiting its applicability for an embedded system.…”

Section: Introductionmentioning

confidence: 99%

A Fully Convolutional Neural Network for Speech Enhancement

Park¹,

Lee²

2017

Interspeech 2017

302

167

View full text Add to dashboard Cite

In hearing aids, the presence of babble noise degrades hearing intelligibility of human speech greatly. However, removing the babble without creating artifacts in human speech is a challenging task in a low SNR environment. Here, we sought to solve the problem by finding a 'mapping' between noisy speech spectra and clean speech spectra via supervised learning. Specifically, we propose using fully Convolutional Neural Networks, which consist of lesser number of parameters than fully connected networks. The proposed network, Redundant Convolutional Encoder Decoder (R-CED), demonstrates that a convolutional network can be 12 times smaller than a recurrent network and yet achieves better performance, which shows its applicability for an embedded system: the hearing aids.

show abstract

Section: Introductionmentioning

confidence: 99%

A Fully Convolutional Neural Network for Speech Enhancement

Park¹,

Lee²

2017

Interspeech 2017

302

167

View full text Add to dashboard Cite

show abstract

“…DBNs ( [136]), DNNs ( [300]) CNNs ( [301]), LSTM ( [302]) AEs ( [303]), VAEs ( [183]) DAEs ( [147]- [149], [304], [305]) SR DBNs ( [136]), DAEs ( [306]), VAEs ( [46], [146], [307], [308]), AL ( [161]), GAN ( [309]) SER AEs ( [152]- [154], [310]), DAEs [155], [156], VAEs [79], [311] 197]), DAE ( [196]), GANs ( [198]) SER DBNs [317], CNNs ( [318]), AL ( [201], [319], [320]), AEs [118], [199], [200], [321], [322] Multi-Task Learning ASR To learn common representations using multi-objective training.…”

Section: B Performance Issues Of Domain Invariant Featuresmentioning

confidence: 99%

Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends

Latif,

Rana,

Khalifa

et al. 2020

Preprint

View full text Add to dashboard Cite

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to make prediction and classification decisions. There are two main drawbacks to this approach: firstly, the feature engineering being manual is cumbersome and requires human knowledge; and secondly, the designed features might not be best for the objective at hand. This has motivated the adoption of a recent trend in speech community towards utilisation of representation learning techniques, which can learn an intermediate representation of the input signal automatically that better suits the task at hand and hence lead to improved performance. The significance of representation learning has increased with advances in deep learning (DL), where the representations are more useful and less dependent on human knowledge, making it very conducive for tasks like classification, prediction, etc. The main contribution of this paper is to present an up-to-date and comprehensive survey on different techniques of speech representation learning by bringing together the scattered research across three distinct research areas including Automatic Speech Recognition (ASR), Speaker Recognition (SR), and Speaker Emotion Recognition (SER). Recent reviews in speech have been conducted for ASR, SR, and SER, however, none of these has focused on the representation learning from speech-a gap that our survey aims to bridge. We also highlight different challenges and the key characteristics of representation learning models and discuss important recent advancements and point out future trends. Our review can be used by the speech research community as an essential resource to quickly grasp the current progress in representation learning and can also act as a guide for navigating study in this area of research.

show abstract

“…Traditional speech enhancement methods [6,7] -sometimes combined with acoustic echo suppression [8] -can help reduce the effect of stationary noise, but have been mostly unable to remove highly non-stationary noise. In recent years, deep-learning-based speech enhancement systems have emerged as state-of-the-art solutions [9,10,11,12,13]. Even more recently, deep-learning-based residual echo suppression algorithms have also demonstrated stateof-the-art performance [14,15].…”

Section: Introductionmentioning

confidence: 99%

Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet

Valin¹,

Tenneti²,

Helwani³

et al. 2021

Preprint

View full text Add to dashboard Cite

Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from hands-free communication systems. This is a challenging problem due to both real-world constraints like loudspeaker non-linearities, and to limited compute capabilities in some communication systems. In this work, we propose a system combining a traditional acoustic echo canceller, and a low-complexity joint residual echo and noise suppressor based on a hybrid signal processing/deep neural network (DSP/DNN) approach. We show that the proposed system outperforms both traditional and other neural approaches, while requiring only 5.5% CPU for real-time operation. We further show that the system can scale to even lower complexity levels.

show abstract

Speech enhancement with weighted denoising auto-encoder

Cited by 36 publications

References 0 publications

A Fully Convolutional Neural Network for Speech Enhancement

A Fully Convolutional Neural Network for Speech Enhancement

Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends

Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet

Contact Info

Product

Resources

About