English
Related papers

Related papers: Attention or Convolution: Transformer Encoders in …

200 papers

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

This document provides a brief introduction to the attention mechanism used in modern language models based on the Transformer architecture. We first illustrate how text is encoded as vectors and how the attention mechanism processes these…

Numerical Analysis · Mathematics 2026-04-02 Michel Fabrice Serret

Over the past two decades, CNN architectures have produced compelling models of sound perception and cognition, learning hierarchical organizations of features. Analogous to successes in computer vision, audio feature classification can be…

Sound · Computer Science 2025-05-13 Prateek Verma , Jonathan Berger

Convolutions operate only locally, thus failing to model global interactions. Self-attention is, however, able to learn representations that capture long-range dependencies in sequences. We propose a network architecture for audio…

Sound · Computer Science 2021-08-27 Nathanaël Carraz Rakotonirina

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-28 Xinmeng Xu , Jianjun Hao

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g.,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-30 Suwon Shon , Felix Wu , Kwangyoun Kim , Prashant Sridhar , Karen Livescu , Shinji Watanabe

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has…

Computation and Language · Computer Science 2021-09-16 Katrin Tomanek , Vicky Zayats , Dirk Padfield , Kara Vaillancourt , Fadi Biadsy

The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-16 Xinyuan Zhou , Grandee Lee , Emre Yılmaz , Yanhua Long , Jiaen Liang , Haizhou Li

In this paper, we present a novel architecture to realize fine-grained style control on the transformer-based text-to-speech synthesis (TransformerTTS). Specifically, we model the speaking style by extracting a time sequence of local style…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-18 Li-Wei Chen , Alexander Rudnicky

Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a pretrained model for arbitrary downstream tasks. However it…

Computation and Language · Computer Science 2019-09-12 Zachary M. Ziegler , Luke Melas-Kyriazi , Sebastian Gehrmann , Alexander M. Rush

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…

Sound · Computer Science 2022-06-22 Junyi Ao , Ziqiang Zhang , Long Zhou , Shujie Liu , Haizhou Li , Tom Ko , Lirong Dai , Jinyu Li , Yao Qian , Furu Wei

Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in…

Computation and Language · Computer Science 2022-04-20 Belen Alastruey , Javier Ferrando , Gerard I. Gállego , Marta R. Costa-jussà

We live in a world where 60% of the population can speak two or more languages fluently. Members of these communities constantly switch between languages when having a conversation. As automatic speech recognition (ASR) systems are being…

Computation and Language · Computer Science 2021-02-16 Siddharth Dalmia , Yuzong Liu , Srikanth Ronanki , Katrin Kirchhoff

In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-01 Alan Baade , Puyuan Peng , David Harwath

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

Computation and Language · Computer Science 2025-01-07 Jiahui Zhao , Hao Shi , Chenrui Cui , Tianrui Wang , Hexin Liu , Zhaoheng Ni , Lingxuan Ye , Longbiao Wang

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Computation and Language · Computer Science 2019-04-08 Jie Hao , Xing Wang , Baosong Yang , Longyue Wang , Jinfeng Zhang , Zhaopeng Tu

We study speech intent classification and slot filling (SICSF) by proposing to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model, which achieves the new state-of-the-art…

Computation and Language · Computer Science 2023-07-17 He Huang , Jagadeesh Balam , Boris Ginsburg

Prior works have investigated the use of articulatory features as complementary representations for automatic speech recognition (ASR), but their use was largely confined to shallow acoustic models. In this work, we revisit articulatory…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-13 Ahmed Adel Attia , Jing Liu , Carol Espy Wilson