English
Related papers

Related papers: Efficient Conformer with Prob-Sparse Attention Mec…

200 papers

A growing intuition in machine learning suggests a link between sparsity and interpretability. We introduce a novel self-ablation mechanism to investigate this connection ante-hoc in the context of language transformers. Our approach…

Machine Learning · Computer Science 2025-05-02 Jeremias Ferrao , Luhan Mikaelson , Keenan Pepper , Natalia Perez-Campanero Antolin

Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR).…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Kwangyoun Kim , Felix Wu , Yifan Peng , Jing Pan , Prashant Sridhar , Kyu J. Han , Shinji Watanabe

As large language models scale to longer contexts, loading the growing KV cache during attention computation becomes a critical bottleneck. Previous work has shown that attention computation is dominated by a small subset of tokens. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-13 Di Liu , Ruitian Wang , Chen Chen , Mingliang Gong , Yongjie Yuan , Han Zhao , Yu Feng , Quan Chen , Minyi Guo

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Machine Learning · Computer Science 2026-01-21 Phani Kumar , Nyshadham , Jyothendra Varma , Polisetty V R K , Aditya Rathore

End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Maxime Burchi , Radu Timofte

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Chunyang Wu , Yongqiang Wang , Yangyang Shi , Ching-Feng Yeh , Frank Zhang

In this paper, we present an in-depth study on online attention mechanisms and distillation techniques for dual-mode (i.e., joint online and offline) ASR using the Conformer Transducer. In the dual-mode Conformer Transducer model, layers…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-23 Felix Weninger , Marco Gaudesi , Md Akmal Haidar , Nicola Ferri , Jesús Andrés-Ferrer , Puming Zhan

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-14 Salah Zaiem , Robin Algayres , Titouan Parcollet , Slim Essid , Mirco Ravanelli

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown…

Computation and Language · Computer Science 2019-10-03 Kyu J. Han , Ramon Prieto , Kaixing Wu , Tao Ma

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which…

Computation and Language · Computer Science 2022-12-21 Roshan Sharma , Bhiksha Raj

Conformer models maintain a large number of internal states, the vast majority of which are associated with self-attention layers. With limited memory bandwidth, reading these from memory at each inference step can slow down inference. In…

Computation and Language · Computer Science 2023-04-04 Rami Botros , Anmol Gulati , Tara N. Sainath , Krzysztof Choromanski , Ruoming Pang , Trevor Strohman , Weiran Wang , Jiahui Yu

This paper presents our recent effort on end-to-end speaker-attributed automatic speech recognition, which jointly performs speaker counting, speech recognition and speaker identification for monaural multi-talker audio. Firstly, we…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-07 Naoyuki Kanda , Guoli Ye , Yashesh Gaur , Xiaofei Wang , Zhong Meng , Zhuo Chen , Takuya Yoshioka

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Computation and Language · Computer Science 2022-04-22 Marcos Treviso , António Góis , Patrick Fernandes , Erick Fonseca , André F. T. Martins

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-16 Jiajun Deng , Xurong Xie , Tianzi Wang , Mingyu Cui , Boyang Xue , Zengrui Jin , Guinan Li , Shujie Hu , Xunying Liu

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Computation and Language · Computer Science 2021-05-04 Jinchuan Tian , Rongzhi Gu , Helin Wang , Yuexian Zou

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy…

Computation and Language · Computer Science 2023-06-01 Huiqiang Jiang , Li Lyna Zhang , Yuang Li , Yu Wu , Shijie Cao , Ting Cao , Yuqing Yang , Jinyu Li , Mao Yang , Lili Qiu

Self-attention is a key enabler of state-of-art accuracy for various transformer-based Natural Language Processing models. This attention mechanism calculates a correlation score for each word with respect to the other words in a sentence.…

Computation and Language · Computer Science 2022-04-18 Zheng Li , Soroush Ghodrati , Amir Yazdanbakhsh , Hadi Esmaeilzadeh , Mingu Kang

End-to-end speech recognition has become popular in recent years, since it can integrate the acoustic, pronunciation and language models into a single neural network. Among end-to-end approaches, attention-based methods have emerged as…

Sound · Computer Science 2020-06-03 Zhifu Gao , Shiliang Zhang , Ming Lei , Ian McLoughlin