# Mutually-Constrained Monotonic Multihead Attention for Online ASR

arXiv: https://arxiv.org/abs/2103.14302 · HTML: https://mlsanity.com/paper/2103.14302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [Monotonic Chunkwise Attention](https://mlsanity.com/paper/1712.05382/) (2017)
- [CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition](https://mlsanity.com/paper/1905.11235/) (2019)
- [Streaming automatic speech recognition with the transformer model](https://mlsanity.com/paper/2001.02674/) (2020)
- [RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation](https://mlsanity.com/paper/1905.03072/) (2019)
- [Transformers with convolutional context for ASR](https://mlsanity.com/paper/1904.11660/) (2019)
- [Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping](https://mlsanity.com/paper/1902.06450/) (2019)
- [Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture](https://mlsanity.com/paper/2001.08290/) (2020)
- [Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR](https://mlsanity.com/paper/2004.05009/) (2020)
- [Enhancing Monotonic Multihead Attention for Streaming ASR](https://mlsanity.com/paper/2005.09394/) (2020)
- [Streaming Transformer ASR with Blockwise Synchronous Beam Search](https://mlsanity.com/paper/2006.14941/) (2020)

## Abstract (arXiv)

Despite the feature of real-time decoding, Monotonic Multihead Attention (MMA) shows comparable performance to the state-of-the-art offline methods in machine translation and automatic speech recognition (ASR) tasks. However, the latency of MMA is still a major issue in ASR and should be combined with a technique that can reduce the test latency at inference time, such as head-synchronous beam search decoding, which forces all non-activated heads to activate after a small fixed delay from the first head activation. In this paper, we remove the discrepancy between training and test phases by considering, in the training of MMA, the interactions across multiple heads that will occur in the test time. Specifically, we derive the expected alignments from monotonic attention by considering the boundaries of other heads and reflect them in the learning process. We validate our proposed method on the two standard benchmark datasets for ASR and show that our approach, MMA with the mutually-constrained heads from the training stage, provides better performance than baselines.