# Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering

arXiv: https://arxiv.org/abs/2506.04981 · HTML: https://mlsanity.com/paper/2506.04981/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 14 of 14)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models](https://mlsanity.com/paper/2405.20541/) (2024)
- [Iterative Pseudo-Labeling for Speech Recognition](https://mlsanity.com/paper/2005.09267/) (2020)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [SlimIPL: Language-Model-Free Iterative Pseudo-Labeling](https://mlsanity.com/paper/2010.11524/) (2020)
- [Lhotse: a speech data representation library for the modern deep learning ecosystem](https://mlsanity.com/paper/2110.12561/) (2021)
- [Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning](https://mlsanity.com/paper/2110.00165/) (2021)
- [Pseudo Label Is Better Than Human Label](https://mlsanity.com/paper/2203.12668/) (2022)
- [Semi-Supervised Formality Style Transfer with Consistency Training](https://mlsanity.com/paper/2203.13620/) (2022)
- [Continuous Pseudo-Labeling from the Start](https://mlsanity.com/paper/2210.08711/) (2022)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)

## Built on by (most cited first, 2 of 2)

- [ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models](https://mlsanity.com/paper/2602.18721/) (2026)
- [StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition](https://mlsanity.com/paper/2608.13717/) (2026)

## Abstract (arXiv)

Fine-tuning pretrained ASR models for specific domains is challenging when labeled data is scarce. But unlabeled audio and labeled data from related domains are often available. We propose an incremental semi-supervised learning pipeline that first integrates a small in-domain labeled set and an auxiliary dataset from a closely related domain, achieving a relative improvement of 4% over no auxiliary data. Filtering based on multi-model consensus or named entity recognition (NER) is then applied to select and iteratively refine pseudo-labels, showing slower performance saturation compared to random selection. Evaluated on the multi-domain Wow call center and Fisher English corpora, it outperforms single-step fine-tuning. Consensus-based filtering outperforms other methods, providing up to 22.3% relative improvement on Wow and 24.8% on Fisher over single-step fine-tuning with random selection. NER is the second-best filter, providing competitive performance at a lower computational cost.