English
Related papers

Related papers: Knowledge Transfer and Distillation from Autoregre…

200 papers

Autoregressive (AR) models remain widely used in time series analysis due to their interpretability, but convencional parameter estimation methods can be computationally expensive and prone to convergence issues. This paper proposes a…

Machine Learning · Statistics 2026-03-20 Anaísa Lucena , Ana Martins , Armando J. Pinho , Sónia Gouveia

This article describes an efficient end-to-end speech translation (E2E-ST) framework based on non-autoregressive (NAR) models. End-to-end speech translation models have several advantages over traditional cascade systems such as inference…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-10 Hirofumi Inaguma , Yosuke Higuchi , Kevin Duh , Tatsuya Kawahara , Shinji Watanabe

Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both…

Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and propose the latency-controlled NAS for acoustic modeling.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-15 Liqiang He , Shulin Feng , Dan Su , Dong Yu

With computers getting more and more powerful and integrated in our daily lives, the focus is increasingly shifting towards more human-friendly interfaces, making Automatic Speech Recognition (ASR) a central player as the ideal means of…

Sound · Computer Science 2021-01-25 Dennis Pinto , Jose-María Arnau , Antonio González

Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality…

Computation and Language · Computer Science 2023-03-15 Pei Guo , Yisheng Xiao , Juntao Li , Min Zhang

Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and…

Information Retrieval · Computer Science 2021-01-25 Sebastian Hofstätter , Sophia Althammer , Michael Schröder , Mete Sertkan , Allan Hanbury

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge distillation and the…

Machine Learning · Computer Science 2026-03-17 Israel Mason-Williams , Gabryel Mason-Williams , Helen Yannakoudakis

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

Machine Learning · Computer Science 2020-11-24 Hadi Pouransari , Mojan Javaheripi , Vinay Sharma , Oncel Tuzel

Knowledge distillation is an approach to transfer information on representations from a teacher to a student by reducing their difference. A challenge of this approach is to reduce the flexibility of the student's representations inducing…

Computation and Language · Computer Science 2024-10-28 Hee-Jun Jung , Doyeon Kim , Seung-Hoon Na , Kangil Kim

Deep convolutional neural networks continue to advance the state-of-the-art in many domains as they grow bigger and more complex. It has been observed that many of the parameters of a large network are redundant, allowing for the…

Computer Vision and Pattern Recognition · Computer Science 2016-12-05 Jonathan Shen , Noranart Vesdapunt , Vishnu N. Boddeti , Kris M. Kitani

Knowledge Distillation is a technique which aims to utilize dark knowledge to compress and transfer information from a vast, well-trained neural network (teacher model) to a smaller, less capable neural network (student model) with improved…

Computer Vision and Pattern Recognition · Computer Science 2022-01-28 Fahad Rahman Amik , Ahnaf Ismat Tasin , Silvia Ahmed , M. M. Lutfe Elahi , Nabeel Mohammed

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Machine Learning · Computer Science 2026-01-12 Pattarawat Chormai , Ali Hashemi , Klaus-Robert Müller , Grégoire Montavon

Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…

Computer Vision and Pattern Recognition · Computer Science 2019-03-13 Tong He , Chunhua Shen , Zhi Tian , Dong Gong , Changming Sun , Youliang Yan

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial…

Machine Learning · Computer Science 2019-04-26 Shu Changyong , Li Peng , Xie Yuan , Qu Yanyun , Dai Longquan , Ma Lizhuang

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant…

Machine Learning · Computer Science 2025-06-17 Chuanhong Liu , Caili Guo , Yang Yang , Mingzhe Chen , Tony Q. S. Quek

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Roy Miles , Ismail Elezi , Jiankang Deng

While autoregressive (AR) LLM-based ASR systems achieve strong accuracy, their sequential decoding limits parallelism and incurs high latency. We propose NLE, a non-autoregressive (NAR) approach that formulates speech recognition as…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-10 Avihu Dekel , Samuel Thomas , Takashi Fukada , George Saon

The goal of this work is to train strong models for visual speech recognition without requiring human annotated ground truth data. We achieve this by distilling from an Automatic Speech Recognition (ASR) model that has been trained on a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Triantafyllos Afouras , Joon Son Chung , Andrew Zisserman

Adder Neural Networks (ANNs) which only contain additions bring us a new way of developing deep neural networks with low energy consumption. Unfortunately, there is an accuracy drop when replacing all convolution filters by adder filters.…

Computer Vision and Pattern Recognition · Computer Science 2020-10-16 Yixing Xu , Chang Xu , Xinghao Chen , Wei Zhang , Chunjing Xu , Yunhe Wang