Challenge: Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts.
Approach: They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios.
Outcome: Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines.

Similar Papers

Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech (2024.emnlp-main)

Copied to clipboard

Challenge: Current ASR TTA methods focus on non-continual TTA, which limits cross-sample knowledge learning compared to continual TTA.
Approach: They propose a Fast-slow TTA framework that leverages the advantage of continual and non-continual TTA and a Dynamic SUTA method that automatically detects domain shifts and resets the model.
Outcome: The proposed method outperforms non-continual and continual TTA methods while maintaining robustness to domain shifts without requiring domain boundary information.
Advancing Test-Time Adaptation in Wild Acoustic Test Settings (2024.emnlp-main)

Copied to clipboard

Challenge: Existing wild vision TTA methods fail to handle speech data due to the unique characteristics of high-entropy speech frames, which are unreliably filtered out even when containing crucial semantic content.
Approach: They propose a method for acoustic foundation models to perform confidence-based adaptation in wild acustic test settings.
Outcome: The proposed method outperforms baselines under Gaussian noise, environmental sounds, accent variations, and sung speech in the wild.
STAF: Pushing the Boundaries of Test-Time Adaptation towards Practical Noise Scenarios (2024.lrec-main)

Copied to clipboard

Challenge: Pre-trained language models have demonstrated superior performance on NLP tasks . however, when the training domain and testing domain are taken from different distributions, the deployed model often violates this assumption.
Approach: They propose a Stable Test-time Adaptation Framework to stabilize the adaptation process.
Outcome: The proposed framework boosts model robustness to noise distribution shifts while minimizing error accumulation and catastrophic forgetting.
Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering (2023.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) have achieved great success in question answering, but their robustness is insufficient to support their practical applications.
Approach: They propose a method which regularizes the model's output and an efficient side block to reduce its inference time.
Outcome: The proposed method achieves comparable or better results than previous TTA methods at a speed close to vanilla forward propagation, which is 1.8 to 4.4 speedup compared to previous methods.
Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages (2026.findings-acl)

Copied to clipboard

Challenge: Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but their performance drops substantially on low-resourced languages due to the limited data availability.
Approach: They propose a Depth-Aware Model Adaptation framework that allocates adaptation capacity according to each layer’s role.
Outcome: The proposed framework matches or surpasses state-of-the-art accuracy with 80% fewer trainable parameters and achieves 29% error reduction under extreme data scarcity.
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models (L18-1)

Copied to clipboard

Challenge: Existing speaker adaptation algorithms for BLSTM-CTC AMs are lacking . TED-LIUM corpus shows speaker adaptation provides 11-20% word error rate reduction over baseline model built on raw filter-bank features.
Approach: They propose to use feature-space adaptation techniques for bidirectional long short term memory (BLSTM) recurrent neural network based acoustic models trained with the connectionist temporal classification objective function to improve speaker adaptation.
Outcome: The proposed approach provides up to 11-20% of word error reduction over baseline models on the TED-LIUM corpus.
Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)

Copied to clipboard

Challenge: Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference.
Approach: They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference.
Outcome: The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains.
No Label? No Problem: Unsupervised Continual Learning for Adaptive Medical ASR (2026.eacl-industry)

Copied to clipboard

Challenge: Medical audio often contains specialized terminology, such as medication names, which existing ASR systems struggle to transcribe accurately.
Approach: They propose an unsupervised continual learning ASR framework that adapts to new data while preserving prior knowledge.
Outcome: Experiments on real-world medical audio show that the proposed framework improves over state-of-the-art models.
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher (2026.acl-long)

Copied to clipboard

Challenge: Existing models for text understanding fail to adapt to domain shifts in real-world applications . current models do not improve themselves as they are applied to new domains .
Approach: They propose a continual test-time adaptation framework that adapts to evolving domains . they propose accumulating domains and a refine-then-filter framework to calibrate teacher predictions .
Outcome: The proposed model excels in a teacher-student framework adaptable to evolving domains.
A Unified Speaker Adaptation Approach for ASR (2021.emnlp-main)

Copied to clipboard

Challenge: Adapting a model to target speakers requires a lot of compute and may cause catastrophic forgetting to the existing speakers.
Approach: They propose a unified speaker adaptation approach consisting of feature adaptation and model adaptation.
Outcome: The proposed model outperforms baseline models with 20.58% relative WER reduction and surpasses finetuning method by 2.54% on target speaker adaptation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations