Stableemit: Selection Probability Discount For Reducing Emission Latency Of Streaming Monotonic Attention ASR

Abstract

While attention-based encoder-decoder (AED) models have been successfully extended to the online variants for streaming automatic speech recognition (ASR), such as monotonic chunkwise attention (MoChA), the models still have a large label emission latency because of the unconstrained end-to-end training objective. Previous works tackled this problem by leveraging alignment information to control the timing to emit tokens during training. In this work, we propose a simple alignment-free regularization method, StableEmit, to encourage MoChA to emit tokens earlier. StableEmit discounts the selection probabilities in hard monotonic attention for token boundary detection by a constant factor and regularizes them to recover the total attention mass during training. As a result, the scale of the selection probabilities is increased, and the values can reach a threshold for token emission earlier, leading to a reduction of emission latency and deletion errors. Moreover, StableEmit can be combi

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyinaguma2021stableemit

Related papers

• Fastemit: Low-latency Streaming ASR With Sequence-level Emission Regularization (2020)12.61
• Alignment Knowledge Distillation For Online Streaming Attention-based Speech Recognition (2021)7.16
• Reducing Streaming ASR Model Delay With Self Alignment (2021)6.77
• Streaming Chunk-aware Multihead Attention For Online End-to-end Speech Recognition (2020)8.60
• Minimum Latency Training Strategies For Streaming Sequence-to-sequence ASR (2020)10.07
• Streaming End-to-end Speech Recognition With Jointly Trained Neural Feature Enhancement (2021)5.84
• Chunked Attention-based Encoder-decoder Model For Streaming Speech Recognition (2023)7.81
• Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies Of Large End-to-end Models (2024)5.84