Transformers in speech processing: A survey
The remarkable success of transformers in the field of natural language processing has
sparked the interest of the speech-processing community, leading to an exploration of their …
sparked the interest of the speech-processing community, leading to an exploration of their …
Scaleformer: Iterative multi-scale refining transformers for time series forecasting
The performance of time series forecasting has recently been greatly improved by the
introduction of transformers. In this paper, we propose a general multi-scale framework that …
introduction of transformers. In this paper, we propose a general multi-scale framework that …
Mossformer: Pushing the performance limit of monaural speech separation using gated single-head transformer with convolution-augmented joint self-attentions
S Zhao, B Ma - … 2023-2023 IEEE International Conference on …, 2023 - ieeexplore.ieee.org
Transformer based models have provided significant performance improvements in
monaural speech separation. However, there is still a performance gap compared to a …
monaural speech separation. However, there is still a performance gap compared to a …
Speech separation using an asynchronous fully recurrent convolutional neural network
Recent advances in the design of neural network architectures, in particular those
specialized in modeling sequences, have provided significant improvements in speech …
specialized in modeling sequences, have provided significant improvements in speech …
Exploring self-attention mechanisms for speech separation
Transformers have enabled impressive improvements in deep learning. They often
outperform recurrent and convolutional models in many tasks while taking advantage of …
outperform recurrent and convolutional models in many tasks while taking advantage of …
Resource-efficient separation transformer
Transformers have recently achieved state-of-the-art performance in speech separation.
These models, however, are computationally-demanding and require a lot of learnable …
These models, however, are computationally-demanding and require a lot of learnable …
State-of-the-art analysis of deep learning-based monaural speech source separation techniques
S Soni, RN Yadav, L Gupta - IEEE Access, 2023 - ieeexplore.ieee.org
The monaural speech source separation problem is an important application in the signal
processing field. But recent interaction of deep learning algorithms with signal processing …
processing field. But recent interaction of deep learning algorithms with signal processing …
Resource-Efficient Separation Transformer
Transformers have recently achieved state-of-the-art performance in speech separation.
These models, however, are computationally demanding and require a lot of learnable …
These models, however, are computationally demanding and require a lot of learnable …
Noise-aware network with shared channel-attention encoder and joint constraint for noisy speech separation
L Sun, X Zhou, A Gong, L Ye, P Li, ES Chng - Digital Signal Processing, 2025 - Elsevier
Recently, significant progress has been made in the end-to-end single-channel speech
separation in clean environments. For noisy speech separation, existing research mainly …
separation in clean environments. For noisy speech separation, existing research mainly …
General-purpose speech representation learning through a self-supervised multi-granularity framework
This paper presents a self-supervised learning framework, named MGF, for general-purpose
speech representation learning. In the design of MGF, speech hierarchy is taken into …
speech representation learning. In the design of MGF, speech hierarchy is taken into …