English
Related papers

Related papers: The Dual-Stream Transformer: Channelized Architect…

200 papers

The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion. Our previous study offered a promising direction within end-to-end automatic…

Computation and Language · Computer Science 2019-10-24 Ruizhi Li , Gregory Sell , Xiaofei Wang , Shinji Watanabe , Hynek Hermansky

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

Computation and Language · Computer Science 2020-04-02 Prakhar Thapak , Prodip Hore

Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained…

High Energy Physics - Phenomenology · Physics 2026-05-12 Saurabh Rai , Sanmay Ganguly

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

Machine Learning · Computer Science 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

We revisit a basic question in sequence modeling: is explicit self-attention actually necessary for strong performance and reasoning? We argue that standard multi-head attention is best seen as a form of tensor lifting: hidden vectors are…

Machine Learning · Computer Science 2025-12-23 Zhang Chong

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Laziz U. Abdullaev , Maksim Tkachenko , Tan M. Nguyen

Conformer has proven to be effective in many speech processing tasks. It combines the benefits of extracting local dependencies using convolutions and global dependencies using self-attention. Inspired by this, we propose a more flexible,…

Computation and Language · Computer Science 2022-07-08 Yifan Peng , Siddharth Dalmia , Ian Lane , Shinji Watanabe

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

Sound · Computer Science 2024-09-04 Tathagata Bandyopadhyay

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Computation and Language · Computer Science 2023-11-27 Nathan Brown , Ashton Williamson , Tahj Anderson , Logan Lawrence

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Lei Zhu , Xinjiang Wang , Zhanghan Ke , Wayne Zhang , Rynson Lau

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have…

Computation and Language · Computer Science 2019-04-16 Matthias Sperber , Graham Neubig , Jan Niehues , Alex Waibel

In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jointly fine-tune on the target problem. The resultant…

Computation and Language · Computer Science 2022-04-21 Karan Singla , Daniel Pressel , Ryan Price , Bhargav Srinivas Chinnari , Yeon-Jun Kim , Srinivas Bangalore

Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a sequence is represented by a single vector. By contrast, Transformers have little inductive bias…

Machine Learning · Computer Science 2022-10-26 Aniket Didolkar , Kshitij Gupta , Anirudh Goyal , Nitesh B. Gundavarapu , Alex Lamb , Nan Rosemary Ke , Yoshua Bengio

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Computation and Language · Computer Science 2022-04-08 Zuzana Jelčicová , Marian Verhelst

Transformer-based end-to-end neural speaker diarization (EEND) models utilize the multi-head self-attention (SA) mechanism to enable accurate speaker label prediction in overlapped speech regions. In this study, to enhance the training…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Ye-Rin Jeoung , Joon-Young Yang , Jeong-Hwan Choi , Joon-Hyuk Chang

Audio-Visual Speaker Detection (AVSD) hinges on modeling both individual temporal continuity and inter-personal social context. Existing coupled architectures struggle to reconcile these tasks in shared representation spaces due to…

Multimedia · Computer Science 2026-04-17 Junhao Xiao , Shun Feng , Zhiyu Wu , Jinghan Yu , Haibiao Yao , Zhiyuan Ma , Jianjun Li , Youjun Bao , Yi Chen

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

Computation and Language · Computer Science 2022-10-18 Zekun Wang , Wenhui Wang , Haichao Zhu , Ming Liu , Bing Qin , Furu Wei

Large Language Models (LLMs) built on transformer architectures have transformed natural language processing, achieving remarkable performance across diverse applications. While distributed inference frameworks enable practical deployment…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-22 Lang Xu , Kaushik Kandadi Suresh , Quentin Anthony , Nawras Alnaasan , Dhabaleswar K. Panda

Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-layer dual-decoder…

Computation and Language · Computer Science 2025-05-20 Aditeya Baral , Allen George Ajith , Roshan Nayak , Mrityunjay Abhijeet Bhanja