English
Related papers

Related papers: Dynamic Encoder Transducer: A Flexible Solution Fo…

200 papers

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Shaoshi Ling , Guoli Ye , Rui Zhao , Yifan Gong

Language Models (LMs) struggle with linguistic understanding at the discourse level, even though discourse patterns such as coherence, cohesion, and narrative flow are prevalent in their pre-training data. To improve the discourse…

Computation and Language · Computer Science 2026-02-17 Zachary Bamberger , Ofek Glick , Chaim Baskin , Yonatan Belinkov

The Decision Transformer (DT) has established a powerful sequence modeling approach to offline reinforcement learning. It conditions its action predictions on Return-to-Go (RTG), using it both to distinguish trajectory quality during…

Artificial Intelligence · Computer Science 2026-01-23 Yongyi Wang , Hanyu Liu , Lingfeng Li , Bozhou Chen , Ang Li , Qirui Zheng , Xionghui Yang , Wenxin Li

Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a…

Computation and Language · Computer Science 2022-03-18 Ali Modarressi , Hosein Mohebbi , Mohammad Taher Pilehvar

This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that…

Computation and Language · Computer Science 2024-01-23 Michael Hentschel , Yuta Nishikawa , Tatsuya Komatsu , Yusuke Fujita

This paper proposes a novel procedure for training an encoder-decoder based deep neural network which compresses NxM models into a single model enabling us to dynamically choose the number of encoder and decoder layers for decoding.…

Computation and Language · Computer Science 2019-08-29 Raj Dabre , Atsushi Fujita

The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive…

Computation and Language · Computer Science 2025-10-16 Jan Miller

Recently, several studies reported that dot-product selfattention (SA) may not be indispensable to the state-of-theart Transformer models. Motivated by the fact that dense synthesizer attention (DSA), which dispenses with dot products and…

Sound · Computer Science 2021-07-27 Menglong Xu , Shengqiang Li , Xiao-Lei Zhang

Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder…

Sound · Computer Science 2018-11-02 Zhe Yuan , Zhuoran Lyu , Jiwei Li , Xi Zhou

Non-autoregressive Transformer (NAT) is a family of text generation models, which aims to reduce the decoding latency by predicting the whole sentences in parallel. However, such latency reduction sacrifices the ability to capture…

Computation and Language · Computer Science 2022-06-14 Fei Huang , Tianhua Tao , Hao Zhou , Lei Li , Minlie Huang

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Sound · Computer Science 2020-10-08 Anshuman Tripathi , Jaeyoung Kim , Qian Zhang , Han Lu , Hasim Sak

This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers of self-attention that allow them to capture long range…

Machine Learning · Computer Science 2019-04-18 Ben Krause , Emmanuel Kahembwe , Iain Murray , Steve Renals

Deploying a deep learning model on mobile/IoT devices is a challenging task. The difficulty lies in the trade-off between computation speed and accuracy. A complex deep learning model with high accuracy runs slowly on resource-limited…

Computer Vision and Pattern Recognition · Computer Science 2018-12-31 Xin Li , Shuai Zhang , Bolan Jiang , Yingyong Qi , Mooi Choo Chuah , Ning Bi

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with…

Computation and Language · Computer Science 2021-11-04 Pu-Chin Chen , Henry Tsai , Srinadh Bhojanapalli , Hyung Won Chung , Yin-Wen Chang , Chun-Sung Ferng

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-28 Keqi Deng , Philip C. Woodland

In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages. That is,…

Computation and Language · Computer Science 2019-10-29 Raúl Vázquez , Alessandro Raganato , Jörg Tiedemann , Mathias Creutz

Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still rely on fixed learnable queries and suffer from severe…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Zhengjian Kang , Jun Zhuang , Kangtong Mo , Qi Chen , Rui Liu , Ye Zhang

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Wenfeng Feng , Hongxiang Wang , Jianlong Wang , Xin Zhang , Jingjing Zhao , Yueyue Liang , Xiang Chen , Duokui Han

Balancing efficiency and accuracy is a long-standing problem for deploying deep learning models. The trade-off is even more important for real-time safety-critical systems like autonomous vehicles. In this paper, we propose an effective…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Mao Ye , Gregory P. Meyer , Yuning Chai , Qiang Liu

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Computation and Language · Computer Science 2020-03-25 Alex Bie , Bharat Venkitesh , Joao Monteiro , Md. Akmal Haidar , Mehdi Rezagholizadeh