Data Augmentation and Loss Normalization for Deep Noise Suppression

Braun, Sebastian; Tashev, Ivan

doi:10.1007/978-3-030-60276-5_8

Cited by 58 publications

(46 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This resulted in a 95% confidence interval (CI) of 0.03. We also provided the baseline noise suppressor [30] for the participants to benchmark their methods.…”

Section: Evaluation Methodologymentioning

confidence: 99%

ICASSP 2021 Deep Noise Suppression Challenge

Reddy

Dubey

Gopal

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH 2020 where we open-sourced training and test datasets for researchers to train their noise suppression models. We also open-sourced a subjective evaluation framework and used the tool to evaluate and select the final winners. Many researchers from academia and industry made significant contributions to push the field forward. We also learned that as a research community, we still have a long way to go in achieving excellent speech quality in challenging noisy real-time conditions. In this challenge, we expanded both our training and test datasets. Clean speech in the training set has increased by 200% with the addition of singing voice, emotion data, and non-English languages. The test set has increased by 100% with the addition of singing, emotional, non-English (tonal and non-tonal) languages, and, personalized DNS test clips. There are two tracks with focus on (i) real-time denoising, and (ii) real-time personalized DNS. We present the challenge results at the end.

show abstract

“…This resulted in a 95% confidence interval (CI) of 0.03. We also provided the baseline noise suppressor [30] for the participants to benchmark their methods.…”

Section: Evaluation Methodologymentioning

confidence: 99%

ICASSP 2021 Deep Noise Suppression Challenge

Reddy

Dubey

Gopal

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…As shown in Fig. 1, each training sequence, i. e. predicted and target signals, are normalized by the active target utterance level, to ensure balanced optimization for signal-level dependent losses [11].…”

Section: Enhancement System and Training Objectivementioning

confidence: 99%

“…The network proposed in [11], referred to as NSnet2, consists only of fully connected (FC) and gated recurrent unit (GRU) [18] layers in the format FC-GRU-GRU-FC-FC-FC. All FC layers are followed by rectified linear unit (ReLU) activations, except the last layer has sigmoid activations to predict a constrained suppression gain.…”

Section: Nsnet2mentioning

confidence: 99%

Towards Efficient Models for Real-Time Deep Noise Suppression

Braun

Gamper

Reddy

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality and background noise reduction, the main challenge is to obtain compact enough models, which are resource efficient during inference time. An important but often neglected aspect for data-driven methods is that results can be only convincing when tested on real-world data and evaluated with useful metrics. In this work, we investigate reasonably small recurrent and convolutional-recurrent network architectures for speech enhancement, trained on a large dataset considering also reverberation. We show interesting tradeoffs between computational complexity and the achievable speech quality, measured on real recordings using a highly accurate MOS estimator. It is shown that the achievable speech quality is a function of network complexity, and show which models have better tradeoffs.

show abstract

“…A possible approach is to train, or adapt the models on the noisy data [ 8 ]. This can be done either by collecting application specific data or through the usage of data augmentation strategies [ 9 ]. However, it has to be considered that gathering large noisy datasets is costly and time consuming while, in general, all possible noisy conditions cannot be known a-priori making unfeasible the data augmentation based approach.…”

Section: Introductionmentioning

confidence: 99%

Time-Domain Joint Training Strategies of Speech Enhancement and Intent Classification Neural Models

Ali

Falavigna

Brutti

2022

Sensors

View full text Add to dashboard Cite

Robustness against background noise and reverberation is essential for many real-world speech-based applications. One way to achieve this robustness is to employ a speech enhancement front-end that, independently of the back-end, removes the environmental perturbations from the target speech signal. However, although the enhancement front-end typically increases the speech quality from an intelligibility perspective, it tends to introduce distortions which deteriorate the performance of subsequent processing modules. In this paper, we investigate strategies for jointly training neural models for both speech enhancement and the back-end, which optimize a combined loss function. In this way, the enhancement front-end is guided by the back-end to provide more effective enhancement. Differently from typical state-of-the-art approaches employing on spectral features or neural embeddings, we operate in the time domain, processing raw waveforms in both components. As application scenario we consider intent classification in noisy environments. In particular, the front-end speech enhancement module is based on Wave-U-Net while the intent classifier is implemented as a temporal convolutional network. Exhaustive experiments are reported on versions of the Fluent Speech Commands corpus contaminated with noises from the Microsoft Scalable Noisy Speech Dataset, shedding light and providing insight about the most promising training approaches.

show abstract

Data Augmentation and Loss Normalization for Deep Noise Suppression

Cited by 58 publications

References 17 publications

ICASSP 2021 Deep Noise Suppression Challenge

ICASSP 2021 Deep Noise Suppression Challenge

Towards Efficient Models for Real-Time Deep Noise Suppression

Time-Domain Joint Training Strategies of Speech Enhancement and Intent Classification Neural Models

Contact Info

Product

Resources

About