English
Related papers

Related papers: MossFormer2: Combining Transformer and RNN-Free Re…

200 papers

Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed upper bound. The major limitation of the current dual-path…

Sound · Computer Science 2023-02-24 Shengkui Zhao , Bin Ma

Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parallelization of their computations. Transformers are emerging…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-10 Cem Subakan , Mirco Ravanelli , Samuele Cornell , Mirko Bronzi , Jianyuan Zhong

For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-13 Xinmeng Xu , Jianjun Hao

While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer…

Computation and Language · Computer Science 2025-10-03 Haochen You , Baojing Liu

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion…

Sound · Computer Science 2021-04-27 Xiyun Li , Yong Xu , Meng Yu , Shi-Xiong Zhang , Jiaming Xu , Bo Xu , Dong Yu

Over the last two decades, language modeling has experienced a shift from the use of predominantly recurrent architectures that process tokens sequentially during training and inference to non-recurrent models that process sequence elements…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Sequence classification is essential in NLP for understanding and categorizing language patterns in tasks like sentiment analysis, intent detection, and topic classification. Transformer-based models, despite achieving state-of-the-art…

Computation and Language · Computer Science 2025-09-30 Hongbo Liu , Jia Xu

Transformers have enabled impressive improvements in deep learning. They often outperform recurrent and convolutional models in many tasks while taking advantage of parallel processing. Recently, we proposed the SepFormer, which obtains…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Cem Subakan , Mirco Ravanelli , Samuele Cornell , Francois Grondin , Mirko Bronzi

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-17 Xue Yang , Changchun Bao

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation…

Machine Learning · Computer Science 2019-07-15 Zhiwei Wang , Yao Ma , Zitao Liu , Jiliang Tang

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…

Sound · Computer Science 2021-12-07 Xiaolin Hu , Kai Li , Weiyi Zhang , Yi Luo , Jean-Marie Lemercier , Timo Gerkmann

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…

Machine Learning · Computer Science 2018-11-09 Davide Bacciu , Antonio Carta , Alessandro Sperduti

The CNN-based methods have achieved impressive results in medical image segmentation, but they failed to capture the long-range dependencies due to the inherent locality of the convolution operation. Transformer-based methods are recently…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Xiaohong Huang , Zhifang Deng , Dandan Li , Xueguang Yuan

Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that provably require greater expressive power. Motivated by this limitation, we…

Machine Learning · Computer Science 2026-05-15 Mayank Mishra , Shawn Tan , Ion Stoica , Joseph Gonzalez , Tri Dao

Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One…

Sound · Computer Science 2023-03-13 William Ravenscroft , Stefan Goetze , Thomas Hain

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Machine Learning · Computer Science 2020-07-01 Antonio Carta , Alessandro Sperduti , Davide Bacciu

We introduce a new structure for memory neural networks, called feedforward sequential memory networks (FSMN), which can learn long-term dependency without using recurrent feedback. The proposed FSMN is a standard feedforward neural…

Neural and Evolutionary Computing · Computer Science 2016-01-07 ShiLiang Zhang , Hui Jiang , Si Wei , LiRong Dai

We propose TF-GridNet for speech separation. The model is a novel deep neural network (DNN) integrating full- and sub-band modeling in the time-frequency (T-F) domain. It stacks several blocks, each consisting of an intra-frame full-band…

Recurrent neural networks (RNNs) are becoming the de facto solution for speech recognition. RNNs exploit long-term temporal relationships in data by applying repeated, learned transformations. Unlike fully-connected (FC) layers with single…

Signal Processing · Electrical Eng. & Systems 2019-08-27 Udit Gupta , Brandon Reagen , Lillian Pentecost , Marco Donato , Thierry Tambe , Alexander M. Rush , Gu-Yeon Wei , David Brooks

Monaural source separation is important for many real world applications. It is challenging because, with only a single channel of information available, without any constraints, an infinite number of solutions are possible. In this paper,…

Sound · Computer Science 2015-10-02 Po-Sen Huang , Minje Kim , Mark Hasegawa-Johnson , Paris Smaragdis
‹ Prev 1 2 3 10 Next ›