DeepAI AI Chat
Log In Sign Up

Mutually-Constrained Monotonic Multihead Attention for Online ASR

by   Jaeyun Song, et al.

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.


page 1

page 2

page 3

page 4


Enhancing Monotonic Multihead Attention for Streaming ASR

We investigate a monotonic multihead attention (MMA) by extending hard m...

Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition

This article describes an efficient training method for online streaming...

CTC Alignments Improve Autoregressive Translation

Connectionist Temporal Classification (CTC) is a widely used approach fo...

Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection

With the increased applications of automatic speech recognition (ASR) in...

Monotonic Chunkwise Attention

Sequence-to-sequence models with soft attention have been successfully a...

CTC-synchronous Training for Monotonic Attention Model

Monotonic chunkwise attention (MoChA) has been studied for the online st...