Audio enhancement using local SNR-based sparse binary mask estimation and spectral imputation

Jeon, Kwang Myung; Kim, Hong Kook

doi:10.1016/j.dsp.2017.06.001

Cited by 6 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system processes an in-the-wild speech audio samples and attempts to remove the noise to its greatest extent, based on the identification of the speech surroundings, which is indicated by the negative recording. Considering the same test set evaluation metrics, the experimental [22,74]-in terms of speech distortion, as indicated by the levels of LSD, SDR, and MCD (cf. Table 6).…”

Section: Results On Speech Denoisingmentioning

confidence: 99%

“…According to AudioSet's ontology, excluding the noise recordings labelled as 'Human sounds', we considered 16 198 samples for training, 636 for development, and 714 for test. 8 A variety of evaluation metrics, including log spectral distortion (LSD), signal-todistortion ratio (SDR), perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), Mel cepstral distortion (MCD), and segmental SNR (SSNR), which are widely used in prior work [22], were taken into account to assess the performance of N-HANS in several Signal-to-Noise Ratio (SNR) conditions. As selective noise suppression has not been explored in the literature yet, it is not possible to compare N-HANS performance on selective noise suppression with previous work.…”

Section: Dataset and Evaluation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

N-HANS: A neural network-based toolkit for in-the-wild audio enhancement

Liu

Keren

Parada-Cabaleiro

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

The unprecedented growth of noise pollution over the last decades has raised an always increasing need for developing efficient audio enhancement technologies. Yet, the variety of difficulties related to processing audio sources in-the-wild, such as handling unseen noises or suppressing specific interferences, makes audio enhancement a still open challenge. In this regard, we present (the Neuro-Holistic Audio-eNhancement System), a Python toolkit for in-the-wild audio enhancement that includes functionalities for audio denoising, source separation, and —for the first time in such a toolkit—selective noise suppression. The architecture is specially developed to automatically adapt to different environmental backgrounds and speakers. This is achieved by the use of two identical neural networks comprised of stacks of residual blocks, each conditioned on additional speech- and noise-based recordings through auxiliary sub-networks. Along to a Python API, a command line interface is provided to researchers and developers, both of them carefully documented. Experimental results indicate that achieves great performance w. r. t. existing methods, preserving also the audio quality at a high level; thus, ensuring a reliable usage in real-life application, e. g., for in-the-wild speech processing, which encourages the development of speech-based intelligent technology.

show abstract

Section: Results On Speech Denoisingmentioning

confidence: 99%

Section: Dataset and Evaluation Metricsmentioning

confidence: 99%

N-HANS: A neural network-based toolkit for in-the-wild audio enhancement

Liu

Keren

Parada-Cabaleiro

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…For selective noise suppression, two samples from AudioSet are selected as positive and negative recordings for each noisy sample. Test set evaluation metrics, log spectral distortion (LSD), signal-to-distortion ratio (SDR), perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), mel cepstral distortion (MCD), and segmental SNR (SSNR), which are widely used in prior works such as (Jeon and Kim, 2017), are demonstrated in Table 2 and Table 3 for different input signal-to-noise ratio (SNR) cases.…”

Section: Methodsmentioning

confidence: 99%

N-HANS: Introducing the Augsburg Neuro-Holistic Audio-eNhancement System

Liu,

Keren,

Schuller

2019

Preprint

View full text Add to dashboard Cite

N-HANS is a Python toolkit for in-the-wild audio enhancement, including speech, music, and general audio denoising, separation, and selective noise or source suppression. The functionalities are realised based on two neural network models sharing the same architecture, but trained separately. The models are comprised of stacks of residual blocks, each conditioned on additional speech or environmental noise recordings for adapting to different unseen speakers or environments in real life. In addition to a Python API, a command line interface is provided to researchers and developers, both of which are documented at https://github.com/N-HANS/N-HANS. Experimental results indicate that N-HANS achieves outstanding performance, and ensure its reliable usage in real-life audio and speech-related tasks, reaching very high audio and speech quality.

show abstract

“…Despite good results obtained by machine learning approaches (see [1]- [3] for deep neural network or [4], [5] for dictionary-based methods), there is still room for unsupervised techniques, especially in applications where large enough databases are hardly available for all the types of noise and speech signals that can actually be encountered [6], [7]. This is the case in assisted listening for The associate editor coordinating the review of this manuscript and approving it for publication was Md.…”

Section: Introduction a Context And Motivationmentioning

confidence: 99%

Optimal Bayesian Speech Enhancement by Parametric Joint Detection and Estimation

Pastor

Bey

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose a general framework to estimate short-time spectral amplitudes (STSA) of speech signals in noise by joint speech detection and estimation to remove or reduce background noise, without increasing signal distortion. The approach is motivated by the fact that speech signals have sparse time-frequency representations and can reasonably be assumed not to be present in every timefrequency bin of the time-frequency domain. By combining parametric detection and estimation theories, the main idea is to take into consideration speech presence and absence in each time-frequency bin to improve the performance of Bayesian estimators. In this respect, for three Bayesian estimators, optimal Neyman-Pearson detectors are derived to decide on the absence or presence of speech in each given timefrequency bin. Decisions returned by such detectors are then used to improve the initial estimates. The resulting estimations have been assessed in two scenarios, namely, with and without reference noise power spectrum. The objective tests confirm the relevance of these approaches, both in terms of speech quality and intelligibility. INDEX TERMS Unsupervised speech enhancement, parametric method, joint detection and estimation, Bayesian estimator, minimum mean square error (MMSE).

show abstract

Audio enhancement using local SNR-based sparse binary mask estimation and spectral imputation

Cited by 6 publications

References 27 publications

N-HANS: A neural network-based toolkit for in-the-wild audio enhancement

N-HANS: A neural network-based toolkit for in-the-wild audio enhancement

N-HANS: Introducing the Augsburg Neuro-Holistic Audio-eNhancement System

Optimal Bayesian Speech Enhancement by Parametric Joint Detection and Estimation

Contact Info

Product

Resources

About