English
Related papers

Related papers: Efficiently Train ASR Models that Memorize Less an…

200 papers

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-19 Yingzhu Zhao , Chongjia Ni , Cheung-Chi Leung , Shafiq Joty , Eng Siong Chng , Bin Ma

Sequential recommendations (SR) with transformer-based architectures are widely adopted in real-world applications, where SR models require frequent retraining to adapt to ever-changing user preferences. However, training transformer-based…

Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they copy answers from provided examples instead of learning the…

Computation and Language · Computer Science 2024-10-04 Ameen Ali , Lior Wolf , Ivan Titov

Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs…

Machine Learning · Computer Science 2026-03-19 Jialei Tan , Zheng Lin , Xiangming Cai , Ruoxi Zhu , Zihan Fang , Pingping Chen , Wei Ni

Continual Learning (CL) in Automatic Speech Recognition (ASR) suffers from catastrophic forgetting when adapting to new tasks, domains, or speakers. A common strategy to mitigate this is to store a subset of past data in memory for…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-06 Steven Vander Eeckt , Hugo Van hamme

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

Machine Learning · Computer Science 2024-08-21 Huixiu Jiang , Ling Yang , Yu Bao , Rutong Si , Sikun Yang

The past decade has witnessed great progress in Automatic Speech Recognition (ASR) due to advances in deep learning. The improvements in performance can be attributed to both improved models and large-scale training data. Key to training…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-02-26 Xiaodong Cui , Wei Zhang , Ulrich Finkler , George Saon , Michael Picheny , David Kung

It has been generally assumed in the automatic speech recognition (ASR) literature that it is better for models to have access to wider context windows. Yet, many of the potential reasons this might be true in the supervised setting do not…

Computation and Language · Computer Science 2024-10-28 Sean Robertson , Ewan Dunbar

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Computation and Language · Computer Science 2023-05-30 Florian Mai , Juan Zuluaga-Gomez , Titouan Parcollet , Petr Motlicek

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

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-29 Wanting Huang , Weiran Wang

Large Deep Learning models are compressed and deployed for specific applications. However, current Deep Learning model compression methods do not utilize the information about the target application. As a result, the compressed models are…

Computation and Language · Computer Science 2024-09-10 Rohit Raj Rai , Angana Borah , Amit Awekar

We propose a novel Patched Multi-Condition Training (pMCT) method for robust Automatic Speech Recognition (ASR). pMCT employs Multi-condition Audio Modification and Patching (MAMP) via mixing {\it patches} of the same utterance extracted…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-12 Pablo Peso Parada , Agnieszka Dobrowolska , Karthikeyan Saravanan , Mete Ozay

Continual learning is crucial for applying machine learning in challenging, dynamic, and often resource-constrained environments. However, catastrophic forgetting - overwriting previously learned knowledge when new information is acquired -…

Machine Learning · Computer Science 2025-05-30 Filip Szatkowski , Yaoyue Zheng , Fei Yang , Bartłomiej Twardowski , Tomasz Trzciński , Joost van de Weijer

In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue is addressed in recent methods by storing the important…

Machine Learning · Computer Science 2023-02-06 Gobinda Saha , Kaushik Roy

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-10 Nithin Rao Koluguri , Travis Bartley , Hainan Xu , Oleksii Hrinchuk , Jagadeesh Balam , Boris Ginsburg , Georg Kucsko

Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems. Even with self-supervised learning and pre-training of ASR models, accent invariance is seldom…

Computation and Language · Computer Science 2024-07-08 Darshan Prabhu , Abhishek Gupta , Omkar Nitsure , Preethi Jyothi , Sriram Ganapathy

Principal component regression (PCR) is a useful method for regularizing linear regression. Although conceptually simple, straightforward implementations of PCR have high computational costs and so are inappropriate when learning with large…

Numerical Analysis · Mathematics 2019-03-08 Liron Mor-Yosef , Haim Avron

Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-12 Saurabhchand Bhati , Jesús Villalba , Piotr Żelasko , Laureano Moro-Velazquez , Najim Dehak

Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the…

Machine Learning · Computer Science 2023-06-06 Amirhossein Reisizadeh , Haochuan Li , Subhro Das , Ali Jadbabaie