Benchmarking Fast Domain Adaptation for Unsupervised Speech Units

arXiv:2608.26992 · cs.LG · Submitted 2026-08-27 · Read on arXiv

cs.LG

Submitted: 2026-08-27

Updated: 2026-08-27

Terminology

• Adaptation — 25× in this paper · explained in 1 episode
• Benchmark — 15× in this paper · explained in 2 episodes
• Domain Adaptation — 12× in this paper · explained in 5 episodes
• Representation Learning — 10× in this paper · explained in 2 episodes
• Contrastive Predictive Coding — 5× in this paper
• Predictive Coding — 5× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Adversarial Training — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• SUPERB: Speech processing Universal PERformance Benchmark
• AudioLM: a Language Modeling Approach to Audio Generation
• The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
• The Zero Resource Speech Challenge 2021: Spoken language modelling
• Representation Learning with Contrastive Predictive Coding
• An Unsupervised Autoregressive Model for Speech Representation Learning
• wav2vec: Unsupervised Pre-training for Speech Recognition
• High Fidelity Neural Audio Compression
• Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
• The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
• Unsupervised pretraining transfers well across languages
• Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks