# An Online Attention-based Model for Speech Recognition

arXiv: https://arxiv.org/abs/1811.05247 · HTML: https://mlsanity.com/paper/1811.05247/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2018.

## Built on by (most cited first, 13 of 13)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [Towards Online Continuous Sign Language Recognition and Translation](https://mlsanity.com/paper/2401.05336/) (2024)
- [Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition](https://mlsanity.com/paper/2103.00422/) (2021)
- [WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognition](https://mlsanity.com/paper/2104.03587/) (2021)
- [An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition](https://mlsanity.com/paper/2106.09885/) (2021)
- [EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild](https://mlsanity.com/paper/2502.14892/) (2025)
- [Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition](https://mlsanity.com/paper/2102.07259/) (2021)
- [A study of latent monotonic attention variants](https://mlsanity.com/paper/2103.16710/) (2021)
- [A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition](https://mlsanity.com/paper/2304.07611/) (2023)
- [Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation](https://mlsanity.com/paper/2501.00868/) (2025)
- [Monotonic segmental attention for automatic speech recognition](https://mlsanity.com/paper/2210.14742/) (2022)
- [Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition](https://mlsanity.com/paper/2209.15176/) (2022)
- [Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition](https://mlsanity.com/paper/2302.09723/) (2023)

## Abstract (arXiv)

Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work, researchers have shown that such architectures can acquire comparable results to state-of-the-art ASR systems, especially when using a bidirectional encoder and global soft attention (GSA) mechanism. However, bidirectional encoder and GSA are two obstacles for real-time speech recognition. In this work, we aim to stream LAS baseline by removing the above two obstacles. On the encoder side, we use a latency-controlled (LC) bidirectional structure to reduce the delay of forward computation. Meanwhile, an adaptive monotonic chunk-wise attention (AMoChA) mechanism is proposed to replace GSA for the calculation of attention weight distribution. Furthermore, we propose two methods to alleviate the huge performance degradation when combining LC and AMoChA. Finally, we successfully acquire an online LAS model, LC-AMoChA, which has only 3.5% relative performance reduction to LAS baseline on our internal Mandarin corpus.