Domain Adaptation

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 157% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 251

All topics

WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers
Sep 12, 2025Akshat Pandey, Karun Kumar, Raphael TangDomain Adaptation Text-Only Adaptation
Comcast · Speech AI · Washington, D.C., USA +3
SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Jul 24, 2025Ye-Chan Kim, SeungJu Cha, Si-Woo Kim +2Domain Adaptation Photorealistic Style Transfer
Hanyang University
When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts
Jul 19, 2025Wooseok Ha, Yuansi ChenDomain Adaptation Target Domain
Department of Mathematical Sciences, KAIST · Department of Mathematics, ETH Zürich
Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
Apr 24, 2025Yang Liu, Kejia Zhang, Bingjie Yan +11Domain Adaptation Collaboration
The Hong Kong Polytechnic University, China · Institute for AI Industry Research, Tsinghua University, China · Institute for AI Industry Research, Tsinghua University, China and Shanghai Jiao Tong University, China +3
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
Apr 19, 2025Jindong Li, Yongguang Li, Yali Fu +4Multimodal Domain Generalization Domain Adaptation
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · The Jilin University, Changchun, China · The Chinese University of Hong Kong, Hong Kong, China +1
AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images
Mar 5, 2025Nimra Dilawar, Sara Nadeem, Javed Iqbal +2Domain Adaptation Few-Shot Segmentation
Intelligent Machines Lab, Department of Artificial Intelligence, Information Technology University, Pakistan
Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability
Feb 24, 2025Wenyuan Wu, Yuan Sun, Yingke Chen +4Adversarial Training Dataset Distillation
College of Computer Science, Sichuan University, China · Department of Computer and Information Sciences, Northumbria University, UK · School of Artificial Intelligence, Sichuan University, China
C-DiffSET: Leveraging Latent Diffusion for SAR-to-EO Image Translation with Confidence-Guided Reliable Object Generation
Nov 16, 2024Jeonghyeok Do, Jaehyup Lee, Munchurl KimUnpaired Image-To-Image Translation Synthetic Aperture Radar
KAIST · KNU
ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving
Nov 3, 2024Salman Khan, Izzeddin Teeti, Reza Javanmard Alitappeh +5Waymo Open Motion Dataset Autonomous Driving
Oxford Brookes University · MAZUST · University of Oxford +2
DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised
Nov 13, 2023Abanoub Ghobrial, Kerstin EderDomain Adaptation Self-Supervised Learning
University of Bristol, Bristol, UK
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
Date pendingHaoyu Wang, Xingyu Yu, Haiyan Zhao +2Large Language Model Quantization Quantization-Aware Training
Department of Computer Science and Technology, Tsinghua University, Beijing, China · School of Software and Microelectronics, Peking University, Beijing, China · College of Computer Science and Technology, National University of Defense Technology, Hunan, China.

Sep 12, 2025, cs.CLJ/K move · Enter open · S save

WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers

Akshat Pandey, Karun Kumar, Raphael Tang

Comcast · Speech AI · Washington, D.C., USA+3

Domain Adaptation Text-Only Adaptation

Open paper AskPDF arXiv

Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder-decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encoder is restored, incurring no extra runtime cost. Across four datasets and four ASR models, WhisTLE alone helps in 28 of 32 (88%) cases, with an average relative WER drop of 22%. Using WhisTLE alone or in combination with other adaptation approaches helps in 116 of 144 (81%) cases, with an average additional WER drop of 15%. Given all treatments that improve on baseline scores, WhisTLE helps in 45 of 55 (82%) cases, with an average additional relative WER drop of 16%. WhisTLE with TTS reduces word error rate (WER) by a relative 49% and outperforms all non-WhisTLE baselines in 100 of 112 scenarios. We also find that WhisTLE additively complements any combination of other domain adaptation approaches; we thus recommend the inclusion of WhisTLE during standard processes for adapting encoder-decoder ASR models. Our code is at https://github.com/akshat0123/WhisTLE

Momentum

Related topics

Latest papers 251