# Are E2E ASR models ready for an industrial usage?

arXiv: https://arxiv.org/abs/2112.12572 · HTML: https://mlsanity.com/paper/2112.12572/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 9 Dec 2021.

## Builds on (most cited first, 21 of 21)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context](https://mlsanity.com/paper/2005.03191/) (2020)
- [Iterative Pseudo-Labeling for Speech Recognition](https://mlsanity.com/paper/2005.09267/) (2020)
- [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020)
- [FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization](https://mlsanity.com/paper/2010.11148/) (2020)
- [LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech](https://mlsanity.com/paper/2104.11462/) (2021)
- [wav2letter++: The Fastest Open-source Speech Recognition System](https://mlsanity.com/paper/1812.07625/) (2018)
- [Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition](https://mlsanity.com/paper/2109.01163/) (2021)
- [Toward domain-invariant speech recognition via large scale training](https://mlsanity.com/paper/1808.05312/) (2018)
- [Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition](https://mlsanity.com/paper/2104.01721/) (2021)
- [Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone](https://mlsanity.com/paper/2103.16776/) (2021)
- [NeMo Inverse Text Normalization: From Development To Production](https://mlsanity.com/paper/2104.05055/) (2021)
- [WER we are and WER we think we are](https://mlsanity.com/paper/2010.03432/) (2020)
- [Efficient conformer-based speech recognition with linear attention](https://mlsanity.com/paper/2104.06865/) (2021)
- [Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition](https://mlsanity.com/paper/2106.09236/) (2021)

## Built on by (most cited first, 3 of 3)

- [Improving Speech Recognition for African American English With Audio Classification](https://mlsanity.com/paper/2309.09996/) (2023)
- [Deep CLAS: Deep Contextual Listen, Attend and Spell](https://mlsanity.com/paper/2409.17603/) (2024)
- [Goodness of Pronunciation Pipelines for OOV Problem](https://mlsanity.com/paper/2209.03787/) (2022)

## Abstract (arXiv)

The Automated Speech Recognition (ASR) community experiences a major turning point with the rise of the fully-neural (End-to-End, E2E) approaches. At the same time, the conventional hybrid model remains the standard choice for the practical usage of ASR. According to previous studies, the adoption of E2E ASR in real-world applications was hindered by two main limitations: their ability to generalize on unseen domains and their high operational cost. In this paper, we investigate both above-mentioned drawbacks by performing a comprehensive multi-domain benchmark of several contemporary E2E models and a hybrid baseline. Our experiments demonstrate that E2E models are viable alternatives for the hybrid approach, and even outperform the baseline both in accuracy and in operational efficiency. As a result, our study shows that the generalization and complexity issues are no longer the major obstacle for industrial integration, and draws the community's attention to other potential limitations of the E2E approaches in some specific use-cases.