English
Related papers

Related papers: FLASepformer: Efficient Speech Separation with Gat…

200 papers

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Computation and Language · Computer Science 2021-06-11 Ivan Chelombiev , Daniel Justus , Douglas Orr , Anastasia Dietrich , Frithjof Gressmann , Alexandros Koliousis , Carlo Luschi

The Transformer architecture has proven to be highly effective for Automatic Speech Recognition (ASR) tasks, becoming a foundational component for a plethora of research in the domain. Historically, many approaches have leaned on…

Sound · Computer Science 2024-04-09 Sizhou Chen , Songyang Gao , Sen Fang

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Yuxuan Liang , Pan Zhou , Roger Zimmermann , Shuicheng Yan

Transformer-based models recently reached state-of-the-art single-channel speech separation accuracy; However, their extreme computational load makes it difficult to deploy them in resource-constrained mobile or IoT devices. We thus present…

Sound · Computer Science 2024-07-02 Hyunseok Oh , Juheon Yi , Youngki Lee

The attention mechanisms of transformers effectively extract pertinent information from the input sequence. However, the quadratic complexity of self-attention w.r.t the sequence length incurs heavy computational and memory burdens,…

Hardware Architecture · Computer Science 2022-06-30 Guan Shen , Jieru Zhao , Quan Chen , Jingwen Leng , Chao Li , Minyi Guo

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Zhaoyang Zhang , Wenqi Shao , Yixiao Ge , Xiaogang Wang , Jinwei Gu , Ping Luo

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Computation and Language · Computer Science 2021-03-23 Hao Peng , Nikolaos Pappas , Dani Yogatama , Roy Schwartz , Noah A. Smith , Lingpeng Kong

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer…

Sound · Computer Science 2022-11-18 Xun Gong , Yu Wu , Jinyu Li , Shujie Liu , Rui Zhao , Xie Chen , Yanmin Qian

For time-frequency (TF) domain speech enhancement (SE) methods, the overlap-and-add operation in the inverse TF transformation inevitably leads to an algorithmic delay equal to the window size. However, typical causal SE systems fail to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-22 Yuewei Zhang , Huanbin Zou , Jie Zhu

The transformer model is known to be computationally demanding, and prohibitively costly for long sequences, as the self-attention module uses a quadratic time and space complexity with respect to sequence length. Many researchers have…

Computation and Language · Computer Science 2025-05-19 Ziwei He , Meng Yang , Minwei Feng , Jingcheng Yin , Xinbing Wang , Jingwen Leng , Zhouhan Lin

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide…

Computation and Language · Computer Science 2020-05-05 Qingqing Cao , Harsh Trivedi , Aruna Balasubramanian , Niranjan Balasubramanian

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

Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation. Traditional approaches always treat these two features separately, ignoring their underlying relationship. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-06 Yihui Fu , Yun Liu , Jingdong Li , Dawei Luo , Shubo Lv , Yukai Jv , Lei Xie

The Transformer has emerged as a versatile and effective architecture with broad applications. However, it still remains an open problem how to efficiently train a Transformer model of high utility with differential privacy guarantees. In…

Machine Learning · Computer Science 2023-05-30 Youlong Ding , Xueyang Wu , Hao Wang , Weike Pan

We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping points) at which efficient Transformer variants become more…

Computation and Language · Computer Science 2023-06-16 Anuj Diwan , Eunsol Choi , David Harwath

This work introduces the Cleanformer, a streaming multichannel neural based enhancement frontend for automatic speech recognition (ASR). This model has a conformer-based architecture which takes as inputs a single channel each of raw and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-05 Joseph Caroselli , Arun Narayanan , Nathan Howard , Tom O'Malley

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin