Streaming Audio-visual Speech Recognition With Alignment Regularization

Abstract

In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. Additionally, we propose a novel alignment regularization technique that promotes synchronization of the audio and visual encoder, which in turn results in better word error rates (WERs) at all SNR levels for streaming and offline AV-ASR models. The proposed AV-ASR model achieves WERs of 2.0% and 2.6% on the Lip Reading Sentences 3 (LRS3) dataset in an offline and online setup, respectively, which both present state-of-the-art results when no external training data are used.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyma2022streaming

Related papers

• Multilingual Audio-visual Speech Recognition With Hybrid CTC/RNN-T Fast Conformer (2024)8.60
• MLCA-AVSR: Multi-layer Cross Attention Fusion Based Audio-visual Speech Recognition (2024)10.07
• Alignment Knowledge Distillation For Online Streaming Attention-based Speech Recognition (2021)7.16
• Streaming Chunk-aware Multihead Attention For Online End-to-end Speech Recognition (2020)8.60
• Online Hybrid Ctc/attention End-to-end Automatic Speech Recognition Architecture (2023)12.99
• Robust End-to-end Deep Audiovisual Speech Recognition (2016)0.00
• Minimum Latency Training Strategies For Streaming Sequence-to-sequence ASR (2020)10.07
• Focus On The Present: A Regularization Method For The ASR Source-target Attention Layer (2020)4.52