English
Related papers

Related papers: FLASepformer: Efficient Speech Separation with Gat…

200 papers

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important.…

Sound · Computer Science 2023-03-08 Zhaoxi Mu , Xinyu Yang , Wenjing Zhu

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

A promising approach to preserving model performance in linearized transformers is to employ position-based re-weighting functions. However, state-of-the-art re-weighting functions rely heavily on target sequence lengths, making it…

Computation and Language · Computer Science 2024-05-24 Victor Agostinelli , Sanghyun Hong , Lizhong Chen

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the Time-Frequency Attention Cache Memory (TFACM) model, which…

Sound · Computer Science 2025-05-20 Guo Chen , Kai Li , Runxuan Yang , Xiaolin Hu

Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output sequences for CTC or RNN-T models. Unfortunately, the long…

Computation and Language · Computer Science 2024-05-22 Wenjing Zhu , Sining Sun , Changhao Shan , Peng Fan , Qing Yang

Linear RNNs with gating recently demonstrated competitive performance compared to Transformers in language modeling. Although their linear compute scaling in sequence length offers theoretical runtime advantages over Transformers, realizing…

Machine Learning · Computer Science 2025-12-30 Maximilian Beck , Korbinian Pöppel , Phillip Lippe , Sepp Hochreiter

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows…

Sound · Computer Science 2023-05-16 Qiquan Zhang , Hongxu Zhu , Qi Song , Xinyuan Qian , Zhaoheng Ni , Haizhou Li

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Yuang Ai , Huaibo Huang , Tao Wu , Qihang Fan , Ran He

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

Most studies on speech enhancement generally don't consider the energy distribution of speech in time-frequency (T-F) representation, which is important for accurate prediction of mask or spectra. In this paper, we present a simple yet…

Sound · Computer Science 2022-03-10 Qiquan Zhang , Qi Song , Zhaoheng Ni , Aaron Nicolson , Haizhou Li

Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. However, their mere aggregation does not lead to…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Zhiyuan Ma , Xiangyu Zhu , Guojun Qi , Chen Qian , Zhaoxiang Zhang , Zhen Lei

Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-07 Ao Sun , Weilin Zhao , Xu Han , Cheng Yang , Zhiyuan Liu , Chuan Shi , Maosong Sun

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studies on speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-24 Vinay Kothapally , John H. L. Hansen

The recently proposed Conformer model has become the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture that captures both local and global features. However, through a series…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Sehoon Kim , Amir Gholami , Albert Shaw , Nicholas Lee , Karttikeya Mangalam , Jitendra Malik , Michael W. Mahoney , Kurt Keutzer

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Zili Wang , Qi Yang , Linsu Shi , Jiazhong Yu , Qinghua Liang , Fei Li , Shiming Xiang