Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model
arXiv:2010.14099
Abstract
Recently, online end-to-end ASR has gained increasing attention. However, the performance of online systems still lags far behind that of offline systems, with a large gap in quality of recognition. For specific scenarios, we can trade-off between performance and latency, and can train multiple systems with different delays to match the performance and latency requirements of various application scenarios. In this work, in contrast to trading-off between performance and latency, we envisage a single system that can match the needs of different scenarios. We propose a novel architecture, termed Universal ASR that can unify streaming and non-streaming ASR models into one system. The embedded streaming ASR model can configure different delays according to requirements to obtain real-time recognition results, while the non-streaming model is able to refresh the final recognition result for better performance. We have evaluated our approach on the public AISHELL-2 benchmark and an industrial-level 20,000-hour Mandarin speech recognition task. The experimental results show that the Universal ASR provides an efficient mechanism to integrate streaming and non-streaming models that can recognize speech quickly and accurately. On the AISHELL-2 task, Universal ASR comfortably outperforms other state-of-the-art systems.
5 pages, 2 figures, submitted to ICASSP 2021
References in corpus (11)
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Attention-Based Models for Speech Recognition
- Sequence Transduction with Recurrent Neural Networks
- Online and Linear-Time Attention by Enforcing Monotonic Alignments
- AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
- ESPnet: End-to-End Speech Processing Toolkit
- Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
- Monotonic Chunkwise Attention
- Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition
- SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition
- An Online Attention-based Model for Speech Recognition