English
Related papers

Related papers: Intermediate-layer output Regularization for Atten…

200 papers

Large language models (LLMs) have shown remarkable generalization across tasks, leading to increased interest in integrating speech with LLMs. These speech LLMs (SLLMs) typically use supervised fine-tuning to align speech with text-based…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-27 Jingran Xie , Xiang Li , Hui Wang , Yue Yu , Yang Xiang , Xixin Wu , Zhiyong Wu

Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL…

Computation and Language · Computer Science 2024-09-30 Chin Yuen Kwok , Jia Qi Yip , Eng Siong Chng

An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic…

Computation and Language · Computer Science 2024-03-14 Yash Sharma , Basil Abraham , Preethi Jyothi

In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the…

Computation and Language · Computer Science 2020-02-06 Alexander H. Liu , Tzu-Wei Sung , Shun-Po Chuang , Hung-yi Lee , Lin-shan Lee

Language recognition tasks are fundamental in natural language processing (NLP) and have been widely used to benchmark the performance of large language models (LLMs). These tasks also play a crucial role in explaining the working…

Machine Learning · Computer Science 2025-05-30 Ruiquan Huang , Yingbin Liang , Jing Yang

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

This paper proposes a novel automatic speech recognition (ASR) framework called Integrated Source-Channel and Attention (ISCA) that combines the advantages of traditional systems based on the noisy source-channel model (SC) and end-to-end…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-02 Qiujia Li , Chao Zhang , Philip C. Woodland

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Xialei Liu , Xusheng Cao , Haori Lu , Jia-wen Xiao , Andrew D. Bagdanov , Ming-Ming Cheng

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Sound · Computer Science 2024-02-09 Sungho Jeon , Ching-Feng Yeh , Hakan Inan , Wei-Ning Hsu , Rashi Rungta , Yashar Mehdad , Daniel Bikel

Active learning (AL) is a label-efficient machine learning paradigm that focuses on selectively annotating high-value instances to maximize learning efficiency. Its effectiveness can be further enhanced by incorporating weak supervision,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Shinnosuke Matsuo , Riku Togashi , Ryoma Bise , Seiichi Uchida , Masahiro Nomura

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-23 Duo Ma , Nana Hou , Van Tung Pham , Haihua Xu , Eng Siong Chng

Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Wei-Hong Li , Steven McDonagh , Ales Leonardis , Hakan Bilen

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Thanh-Dat Truong , Christophe Bobda , Nitin Agarwal , Khoa Luu

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Computation and Language · Computer Science 2025-04-22 Omar Shaikh , Michelle S. Lam , Joey Hejna , Yijia Shao , Hyundong Cho , Michael S. Bernstein , Diyi Yang

Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently performs multiple iterations of pseudo-labeling on…

Computation and Language · Computer Science 2020-08-28 Qiantong Xu , Tatiana Likhomanenko , Jacob Kahn , Awni Hannun , Gabriel Synnaeve , Ronan Collobert

Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Hang Xu , Wei Yu , Jiangtong Tan , Zhen Zou , Feng Zhao

Automatic Speech Recognition (ASR) systems remain prone to errors that affect downstream applications. In this paper, we propose LIR-ASR, a heuristic optimized iterative correction framework using LLMs, inspired by human auditory…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Yutong Liu , Ziyue Zhang , Cheng Huang , Yongbin Yu , Xiangxiang Wang , Yuqing Cai , Nyima Tashi

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a…

Computation and Language · Computer Science 2024-04-04 Anna Langedijk , Hosein Mohebbi , Gabriele Sarti , Willem Zuidema , Jaap Jumelet

We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is trained in a fully end-to-end manner, incorporating speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-20 Jinhan Wang , Weiqing Wang , Kunal Dhawan , Taejin Park , Myungjong Kim , Ivan Medennikov , He Huang , Nithin Koluguri , Jagadeesh Balam , Boris Ginsburg

End-to-End Speech Translation often shows slower convergence and worse performance when target transcriptions exhibit high variance and semantic ambiguity. We propose Listen, Attend, Understand (LAU), a semantic regularization technique…

Computation and Language · Computer Science 2026-01-06 Yacouba Diarra , Michael Leventhal