Speech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks

Kumar, Anurag; Florêncio, Dinei

doi:10.21437/interspeech.2016-88

Cited by 99 publications

(72 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latter seems a promising way to improve objective quality, although both models have to incorporate the standard MSE due to the band limitation of each objective measure. [21] reported that a simple perceptually weighted wide-band MSE alone does not improve objective speech quality or intelligibility, suggesting that the MSE is still a reliable learning objective for wide-band speech enhancement.…”

Section: Introductionmentioning

confidence: 99%

Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement

Xia

Braun

Reddy

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that enhances short-time speech spectra on a single-frame-in, single-frame-out basis, a framework adopted by most classical signal processing methods. We propose two novel mean-squared-error-based learning objectives that enable separate control over the importance of speech distortion versus noise reduction. The proposed loss functions are evaluated by widely accepted objective quality and intelligibility measures and compared to other competitive online methods. In addition, we study the impact of feature normalization and varying batch sequence lengths on the objective quality of enhanced speech. Finally, we show subjective ratings for the proposed approach and a state-of-the-art real-time RNN-based method.

show abstract

Section: Introductionmentioning

confidence: 99%

Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement

Xia

Braun

Reddy

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…We down-sample the input audio from 48 kHz to 16 kHz. And during training, similar to [4], we divided the original audio into overlapped slices with the stride 2 13 , each of which has 2 14 samples (approximately 1 second). During testing, as in [4], we divide the test utterance into non-overlapped slices and concatenate the results as the final enhanced speech for the whole duration.…”

Section: Discriminative Modelmentioning

confidence: 99%

Coarse-to-Fine Optimization for Speech Enhancement

Yao¹,

Al-Dahle²

2019

Interspeech 2019

View full text Add to dashboard Cite

In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the enhanced speech with even the same cosine similarity loss in high dimensional space, a deep neural network learnt with this loss might not be able to predict enhanced speech with good quality. Our coarse-to-fine strategy optimizes the cosine similarity loss for different granularities so that more constraints are added to the prediction from high dimension to relatively low dimension. In this way, the enhanced speech will better resemble the clean speech. Experimental results show the effectiveness of our proposed coarse-to-fine optimization in both discriminative models and generative models. Moreover, we apply the coarse-tofine strategy to the adversarial loss in generative adversarial network (GAN) and propose dynamic perceptual loss, which dynamically computes the adversarial loss from coarse resolution to fine resolution. Dynamic perceptual loss further improves the accuracy and achieves state-of-the-art results compared with other generative models.

show abstract

“…Advances in deep learning recently improved the performance of noise reduction algorithms [1,2,3]. It is common practice to transform the noisy time-domain signal into a time-frequency representation, for instance using a short-time Fourier transform (STFT).…”

Section: Introductionmentioning

confidence: 99%

CLCNET: Deep Learning-Based Noise Reduction for Hearing aids using Complex Linear Coding

Schröter

Rosenkranz

Escalante-B.

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learning-based state-of-the-art algorithms, however, either do not consider real-time and frequency resolution constrains or result in poor quality under very noisy conditions.To improve monaural speech enhancement in noisy environments, we propose CLCNet, a framework based on complex valued linear coding. First, we define complex linear coding (CLC) motivated by linear predictive coding (LPC) that is applied in the complex frequency domain. Second, we propose a framework that incorporates complex spectrogram input and coefficient output. Third, we define a parametric normalization for complex valued spectrograms that complies with low-latency and on-line processing.Our CLCNet was evaluated on a mixture of the EUROM database and a real-world noise dataset recorded with hearing aids and compared to traditional real-valued Wiener-Filter gains.

show abstract

Speech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks

Cited by 99 publications

References 25 publications

Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement

Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement

Coarse-to-Fine Optimization for Speech Enhancement

CLCNET: Deep Learning-Based Noise Reduction for Hearing aids using Complex Linear Coding

Contact Info

Product

Resources

About