# Scaling End-to-End Models for Large-Scale Multilingual ASR

arXiv: https://arxiv.org/abs/2104.14830 · HTML: https://mlsanity.com/paper/2104.14830/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 30 Apr 2021.

## Builds on (most cited first, 30 of 31)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (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)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models](https://mlsanity.com/paper/2010.05874/) (2020)
- [Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters](https://mlsanity.com/paper/2007.03001/) (2020)
- [ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context](https://mlsanity.com/paper/2005.03191/) (2020)
- [Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model](https://mlsanity.com/paper/1909.05330/) (2019)
- [Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling](https://mlsanity.com/paper/1902.08295/) (2019)
- [Balancing Training for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2004.06748/) (2020)
- [A Better and Faster End-to-End Model for Streaming ASR](https://mlsanity.com/paper/2011.10798/) (2020)
- [On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition](https://mlsanity.com/paper/2005.14327/) (2020)
- [Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes](https://mlsanity.com/paper/1811.09021/) (2018)
- [Knowledge Distillation for Multi-task Learning](https://mlsanity.com/paper/2007.06889/) (2020)
- [Advancing RNN Transducer Technology for Speech Recognition](https://mlsanity.com/paper/2103.09935/) (2021)
- [Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model](https://mlsanity.com/paper/1712.01541/) (2017)
- [Massively Multilingual Adversarial Speech Recognition](https://mlsanity.com/paper/1904.02210/) (2019)

## Built on by (most cited first, 30 of 61)

- [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)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [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)
- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data](https://mlsanity.com/paper/2309.13876/) (2023)
- [Joint Unsupervised and Supervised Training for Multilingual ASR](https://mlsanity.com/paper/2111.08137/) (2021)
- [Exploiting Adapters for Cross-lingual Low-resource Speech Recognition](https://mlsanity.com/paper/2105.11905/) (2021)
- [GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement](https://mlsanity.com/paper/2406.11546/) (2024)
- [Improving Massively Multilingual ASR With Auxiliary CTC Objectives](https://mlsanity.com/paper/2302.12829/) (2023)
- [A Configurable Multilingual Model is All You Need to Recognize All Languages](https://mlsanity.com/paper/2107.05876/) (2021)
- [Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification](https://mlsanity.com/paper/2209.06058/) (2022)
- [From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition](https://mlsanity.com/paper/2301.07851/) (2023)
- [Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision](https://mlsanity.com/paper/2406.02166/) (2024)
- [Scaling ASR Improves Zero and Few Shot Learning](https://mlsanity.com/paper/2111.05948/) (2021)
- [Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition](https://mlsanity.com/paper/2112.05820/) (2021)
- [Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities](https://mlsanity.com/paper/2211.05756/) (2022)
- [Learn and Don't Forget: Adding a New Language to ASR Foundation Models](https://mlsanity.com/paper/2407.06800/) (2024)
- [Towards Zero-Shot Code-Switched Speech Recognition](https://mlsanity.com/paper/2211.01458/) (2022)
- [Multi-modal Deep Learning](https://mlsanity.com/paper/2403.03385/) (2024)
- [Efficient Domain Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2302.01496/) (2023)
- [Enabling On-Device Training of Speech Recognition Models with Federated Dropout](https://mlsanity.com/paper/2110.03634/) (2021)
- [Learning ASR pathways: A sparse multilingual ASR model](https://mlsanity.com/paper/2209.05735/) (2022)
- [Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study](https://mlsanity.com/paper/2401.12789/) (2024)

## Abstract (arXiv)

Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data. Existing work has shown positive transfer from high resource to low resource languages. However, degradations on high resource languages are commonly observed due to interference from the heterogeneous multilingual data and reduction in per-language capacity. We conduct a capacity study on a 15-language task, with the amount of data per language varying from 7.6K to 53.5K hours. We adopt GShard [1] to efficiently scale up to 10B parameters. Empirically, we find that (1) scaling the number of model parameters is an effective way to solve the capacity bottleneck - our 500M-param model already outperforms monolingual baselines and scaling it to 1B and 10B brought further quality gains; (2) larger models are not only more data efficient, but also more efficient in terms of training cost as measured in TPU days - the 1B-param model reaches the same accuracy at 34% of training time as the 500M-param model; (3) given a fixed capacity budget, adding depth works better than width and large encoders do better than large decoders; (4) with continuous training, they can be adapted to new languages and domains.