# Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications

arXiv: https://arxiv.org/abs/2010.14665 · HTML: https://mlsanity.com/paper/2010.14665/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 11 of 11)

- [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://mlsanity.com/paper/2101.07597/) (2021)
- [Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey](https://mlsanity.com/paper/2403.01255/) (2024)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Sliced Recursive Transformer](https://mlsanity.com/paper/2111.05297/) (2021)
- [Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency](https://mlsanity.com/paper/2104.02176/) (2021)
- [Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition](https://mlsanity.com/paper/2309.15796/) (2023)
- [Munsit at NADI 2025 Shared Task 2: Pushing the Boundaries of Multidialectal Arabic ASR with Weakly Supervised Pretraining and Continual Supervised Fine-tuning](https://mlsanity.com/paper/2508.08912/) (2025)
- [Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios](https://mlsanity.com/paper/2104.02232/) (2021)
- [Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning](https://mlsanity.com/paper/2504.12254/) (2025)
- [WST: Weakly Supervised Transducer for Automatic Speech Recognition](https://mlsanity.com/paper/2511.04035/) (2025)
- [Survey: Transformer-based Models in Data Modality Conversion](https://mlsanity.com/paper/2408.04723/) (2024)

## Abstract (arXiv)

In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM counterparts on industrial scale tasks. Specifically, we compare Emformer with latency-controlled BLSTM (LCBLSTM) on medium latency tasks and LSTM on low latency tasks. On a low latency voice assistant task, Emformer gets 24% to 26% relative word error rate reductions (WERRs). For medium latency scenarios, comparing with LCBLSTM with similar model size and latency, Emformer gets significant WERR across four languages in video captioning datasets with 2-3 times inference real-time factors reduction.