English
Related papers

Related papers: Audio-AdapterFusion: A Task-ID-free Approach for E…

200 papers

Building a persona-based conversation agent is challenging owing to the lack of large amounts of speaker-specific conversation data for model training. This paper addresses the problem by proposing a multi-task learning approach to training…

Computation and Language · Computer Science 2017-10-23 Yi Luan , Chris Brockett , Bill Dolan , Jianfeng Gao , Michel Galley

As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed, traditional fine-tuning methods are costly, due to the need…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Zijun Long , George Killick , Richard McCreadie , Gerardo Aragon Camarasa

Adapter tuning, which updates only a few parameters, has become a mainstream method for fine-tuning pretrained language models to downstream tasks. However, it often yields subpar results in few-shot learning. AdapterFusion, which assembles…

Computation and Language · Computer Science 2023-08-31 Shwai He , Run-Ze Fan , Liang Ding , Li Shen , Tianyi Zhou , Dacheng Tao

With the advance in self-supervised learning for audio and visual modalities, it has become possible to learn a robust audio-visual speech representation. This would be beneficial for improving the audio-visual speech recognition (AVSR)…

Image and Video Processing · Electrical Eng. & Systems 2022-07-12 Zi-Qiang Zhang , Jie Zhang , Jian-Shu Zhang , Ming-Hui Wu , Xin Fang , Li-Rong Dai

Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data distributions. While these methods have shown promising results, they exhibit notable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Weicai Yan , Xinhua Ma , Wang Lin , Tao Jin

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-03 Desh Raj , Jesus Villalba , Daniel Povey , Sanjeev Khudanpur

Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Yinghui Xing , Dexuan Kong , Shizhou Zhang , Geng Chen , Lingyan Ran , Peng Wang , Yanning Zhang

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

The acoustic and linguistic features are important cues for the spoken language identification (LID) task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. In this paper,…

Computation and Language · Computer Science 2022-08-01 Peng Shen , Xugang Lu , Hisashi Kawai

A joint speech and text optimization method is proposed for hybrid transducer and attention-based encoder decoder (TAED) modeling to leverage large amounts of text corpus and enhance ASR accuracy. The joint TAED (J-TAED) is trained with…

Computation and Language · Computer Science 2025-06-25 Yun Tang , Eesung Kim , Vijendra Raj Apsingekar

Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods. However,…

Sound · Computer Science 2023-10-16 Jian Guan , Youde Liu , Qiuqiang Kong , Feiyang Xiao , Qiaoxi Zhu , Jiantong Tian , Wenwu Wang

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-16 Shubham Toshniwal , Tara N. Sainath , Ron J. Weiss , Bo Li , Pedro Moreno , Eugene Weinstein , Kanishka Rao

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-14 Pavel Denisov , Ngoc Thang Vu

Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks. However, the potential of such multi-task learners has not been exploited during transfer learning. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Chengyue Wu , Teng Wang , Yixiao Ge , Zeyu Lu , Ruisong Zhou , Ying Shan , Ping Luo

The end-to-end ASR model is often desired in the streaming multilingual scenario since it is easier to deploy and can benefit from pre-trained speech models such as powerful foundation models. Meanwhile, the heterogeneous nature and…

Computation and Language · Computer Science 2024-01-18 Junwen Bai , Bo Li , Qiujia Li , Tara N. Sainath , Trevor Strohman

As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks…

Software Engineering · Computer Science 2023-03-29 Deze Wang , Boxing Chen , Shanshan Li , Wei Luo , Shaoliang Peng , Wei Dong , Xiangke Liao

Although great progresses have been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures…

Sound · Computer Science 2018-12-06 Yanmin Qian , Xuankai Chang , Dong Yu

Multilingual speech processing with self-supervised or supervised pre-trained Speech Foundation Models (SFM) has achieved strong performance on tasks like Language Identification (LID) and Automatic Speech Recognition (ASR). However, these…

Sound · Computer Science 2025-06-04 Qingzheng Wang , Jiancheng Sun , Yifan Peng , Shinji Watanabe

Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Yue Han , Junwei Zhu , Keke He , Xu Chen , Yanhao Ge , Wei Li , Xiangtai Li , Jiangning Zhang , Chengjie Wang , Yong Liu

Large pre-trained models have enabled significant advances in machine learning and served as foundation components. Model fusion methods, such as task arithmetic, have been proven to be powerful and scalable to incorporate fine-tuned…

Machine Learning · Computer Science 2024-03-12 Anke Tang , Li Shen , Yong Luo , Yibing Zhan , Han Hu , Bo Du , Yixin Chen , Dacheng Tao