# BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2109.13226 · HTML: https://mlsanity.com/paper/2109.13226/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 106 references that are in the map.
- First posted on arXiv 27 Sep 2021.

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [Mesh-TensorFlow: Deep Learning for Supercomputers](https://mlsanity.com/paper/1811.02084/) (2018)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [Improved Noisy Student Training for Automatic Speech Recognition](https://mlsanity.com/paper/2005.09629/) (2020)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Self-Training for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.09116/) (2019)
- [End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](https://mlsanity.com/paper/1911.08460/) (2019)
- [GSPMD: General and Scalable Parallelization for ML Computation Graphs](https://mlsanity.com/paper/2105.04663/) (2021)
- [Broaden Your Views for Self-Supervised Video Learning](https://mlsanity.com/paper/2103.16559/) (2021)
- [Unsupervised pretraining transfers well across languages](https://mlsanity.com/paper/2002.02848/) (2020)

## Built on by (most cited first, 30 of 88)

- [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)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Joint Audio and Speech Understanding](https://mlsanity.com/paper/2309.14405/) (2023)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks](https://mlsanity.com/paper/2306.07303/) (2023)
- [SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training](https://mlsanity.com/paper/2110.10329/) (2021)
- [Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference](https://mlsanity.com/paper/2304.04947/) (2023)
- [FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion](https://mlsanity.com/paper/2406.06858/) (2024)
- [UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training](https://mlsanity.com/paper/2110.05752/) (2021)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions](https://mlsanity.com/paper/2408.16589/) (2024)
- [Universal Paralinguistic Speech Representations Using Self-Supervised Conformers](https://mlsanity.com/paper/2110.04621/) (2021)
- [Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models](https://mlsanity.com/paper/2406.10507/) (2024)
- [Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?](https://mlsanity.com/paper/2204.12765/) (2022)
- [BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting](https://mlsanity.com/paper/2307.00142/) (2023)
- [Pseudo Label Is Better Than Human Label](https://mlsanity.com/paper/2203.12668/) (2022)
- [Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input](https://mlsanity.com/paper/2210.14648/) (2022)
- [From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition](https://mlsanity.com/paper/2301.07851/) (2023)
- [ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition](https://mlsanity.com/paper/2210.13352/) (2022)
- [Self-supervised representations in speech-based depression detection](https://mlsanity.com/paper/2305.12263/) (2023)
- [TRILLsson: Distilled Universal Paralinguistic Speech Representations](https://mlsanity.com/paper/2203.00236/) (2022)
- [MelHuBERT: A simplified HuBERT on Mel spectrograms](https://mlsanity.com/paper/2211.09944/) (2022)
- [HeAR -- Health Acoustic Representations](https://mlsanity.com/paper/2403.02522/) (2024)

## Abstract (arXiv)

We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of pre-training, self-training and scaling up model size greatly increases data efficiency, even for extremely large tasks with tens of thousands of hours of labeled data. In particular, on an ASR task with 34k hours of labeled data, by fine-tuning an 8 billion parameter pre-trained Conformer model we can match state-of-the-art (SoTA) performance with only 3% of the training data and significantly improve SoTA with the full training set. We also report on the universal benefits gained from using big pre-trained and self-trained models for a large set of downstream tasks that cover a wide range of speech domains and span multiple orders of magnitudes of dataset sizes, including obtaining SoTA performance on many public benchmarks. In addition, we utilize the learned representation of pre-trained networks to achieve SoTA results on non-ASR tasks.