A Conditional Generative Model for Speech Enhancement

Zheng-xi, LI; Dai, Li-Rong; Yan, Shuicheng; McLoughlin, Ian

doi:10.1007/s00034-018-0798-4

Cited by 15 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…* Correspondance email: h.phan@qmul.ac.uk and fake signals, transmits information to G so that G can learn to produce output that resembles the realistic distribution of the clean signals. Using GANs, speech enhancement has been done using either magnitude spectrum input [18] or raw waveform input [14], [15]. Existing speech enhancement GAN (SEGAN) systems share a common feature -the enhancement mapping is accomplished via a single stage by a single generator G [14], [15], [18], which may not be optimal.…”

Section: Introductionmentioning

confidence: 99%

“…Using GANs, speech enhancement has been done using either magnitude spectrum input [18] or raw waveform input [14], [15]. Existing speech enhancement GAN (SEGAN) systems share a common feature -the enhancement mapping is accomplished via a single stage by a single generator G [14], [15], [18], which may not be optimal. Here, we aim to divide the enhancement process into multiple stages and accomplish it via multiple enhancement mappings, one at each stage.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving GANs for Speech Enhancement

Phan

McLoughlin

Pham

et al. 2020

IEEE Signal Process. Lett.

125

View full text Add to dashboard Cite

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement mapping. In this work, we propose to use multiple generators that are chained to perform multi-stage enhancement mapping, which gradually refines the noisy input signals in a stage-wise fashion. Furthermore, we study two scenarios: (1) the generators share their parameters and (2) the generators' parameters are independent. The former constrains the generators to learn a common mapping that is iteratively applied at all enhancement stages and results in a small model footprint. On the contrary, the latter allows the generators to flexibly learn different enhancement mappings at different stages of the network at the cost of an increased model size. We demonstrate that the proposed multi-stage enhancement approach outperforms the one-stage SEGAN baseline, where the independent generators lead to more favorable results than the tied generators. The source code is available at http://github.com/pquochuy/idsegan.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving GANs for Speech Enhancement

Phan

McLoughlin

Pham

et al. 2020

IEEE Signal Process. Lett.

125

View full text Add to dashboard Cite

show abstract

“…Speech enhancement is useful in many applications, such as speech recognition [1,2,3] and hearing aids [4,5]. Recently, the research community has witnessed a shift in methodology from conventional signal processing methods [6,7] to data-driven enhancement approaches, particularly those based on deep learning paradigms [8,9,3,10,11]. Beside discriminative modeling with typical deep network variants, such as deep neural networks (DNNs) [8], convolutional neural networks (CNNs) [9,10], and recurrent neural networks (RNNs) [11,3], generative modeling with GANs [12] have been shown to hold promise for speech enhancement [13,14,15].…”

Section: Introductionmentioning

confidence: 99%

“…Different input types have been exploited, e.g. raw waveform [15,16] and time-frequency image [9,14]. Better losses, like Wasserstein loss [14], relativistic loss [16], and metric loss [14], have been tailored to gain stabilization in the training process.…”

Section: Introductionmentioning

confidence: 99%

Self-Attention Generative Adversarial Network for Speech Enhancement

Phan

Nguyêݱn²,

Chén

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

Existing generative adversarial networks (GANs) for speech enhancement solely rely on the convolution operation, which may obscure temporal dependencies across the sequence input. To remedy this issue, we propose a self-attention layer adapted from non-local attention, coupled with the convolutional and deconvolutional layers of a speech enhancement GAN (SEGAN) using raw signal input. Further, we empirically study the effect of placing the self-attention layer at the (de)convolutional layers with varying layer indices as well as at all of them when memory allows. Our experiments show that introducing self-attention to SEGAN leads to consistent improvement across the objective evaluation metrics of enhancement performance. Furthermore, applying at different (de)convolutional layers does not significantly alter performance, suggesting that it can be conveniently applied at the highest-level (de)convolutional layer with the smallest memory overhead 1 .

show abstract

“…This combines a DBF for extracting robust features with the posteriors of the DNN for improved model capability, obtaining more and better phoneme information for the TV modeling, further enhancing LID performance. These advances clearly demonstrate the relevance of phonetic-aware ASR-trained DNNs to LID, Generative adversarial networks (GANs) [10] have recently become very popular for signal generation processing in areas such as image generation [11], image-to-image translation [12,13,14] and speech enhancement [15]. A GAN consists of a generator that produces fake data from noise, and a discriminator to distinguish between fake and real data.…”

Section: Introductionmentioning

confidence: 99%