# Toward domain-invariant speech recognition via large scale training

arXiv: https://arxiv.org/abs/1808.05312 · HTML: https://mlsanity.com/paper/1808.05312/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2018.

## Built on by (most cited first, 30 of 35)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning](https://mlsanity.com/paper/2110.00165/) (2021)
- [Adaptation of Whisper models to child speech recognition](https://mlsanity.com/paper/2307.13008/) (2023)
- [Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition](https://mlsanity.com/paper/2110.02220/) (2021)
- [Pseudo Label Is Better Than Human Label](https://mlsanity.com/paper/2203.12668/) (2022)
- [Efficient Domain Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2302.01496/) (2023)
- [Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR](https://mlsanity.com/paper/2210.05793/) (2022)
- [Extracting Targeted Training Data from ASR Models, and How to Mitigate It](https://mlsanity.com/paper/2204.08345/) (2022)
- [Modular Domain Adaptation for Conformer-Based Streaming ASR](https://mlsanity.com/paper/2305.13408/) (2023)
- [An analysis of degenerating speech due to progressive dysarthria on ASR performance](https://mlsanity.com/paper/2211.00089/) (2022)
- [Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition](https://mlsanity.com/paper/2409.16954/) (2024)
- [On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech](https://mlsanity.com/paper/2106.10259/) (2021)
- [Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages](https://mlsanity.com/paper/2503.23542/) (2025)
- [Whisper Finetuning on Nepali Language](https://mlsanity.com/paper/2411.12587/) (2024)
- [Are E2E ASR models ready for an industrial usage?](https://mlsanity.com/paper/2112.12572/) (2021)
- [A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection](https://mlsanity.com/paper/2205.05684/) (2022)
- [Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion](https://mlsanity.com/paper/2211.02712/) (2022)
- [E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model](https://mlsanity.com/paper/2211.15432/) (2022)
- [Large-scale unsupervised audio pre-training for video-to-speech synthesis](https://mlsanity.com/paper/2306.15464/) (2023)
- [OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation](https://mlsanity.com/paper/2310.02422/) (2023)
- [A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition](https://mlsanity.com/paper/2311.04936/) (2023)
- [Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers](https://mlsanity.com/paper/2312.11123/) (2023)
- [Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models](https://mlsanity.com/paper/2403.19709/) (2024)
- [Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning](https://mlsanity.com/paper/2504.12254/) (2025)
- [Continual learning using lattice-free MMI for speech recognition](https://mlsanity.com/paper/2110.07055/) (2021)
- [Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition](https://mlsanity.com/paper/2403.19822/) (2024)

## Abstract (arXiv)

Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. This work explores the idea of building a single domain-invariant model for varied use-cases by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate effects like background noise, codec distortion, and sampling rates. Our results show that, even at such a scale, a model thus trained works almost as well as those fine-tuned to specific subsets: A single model can be robust to multiple application domains, and variations like codecs and noise. More importantly, such models generalize better to unseen conditions and allow for rapid adaptation -- we show that by using as little as 10 hours of data from a new domain, an adapted domain-invariant model can match performance of a domain-specific model trained from scratch using 70 times as much data. We also highlight some of the limitations of such models and areas that need addressing in future work.