Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition
| Autor: | Yeh, Ching-Feng, Wang, Yongqiang, Shi, Yangyang, Wu, Chunyang, Zhang, Frank, Chan, Julian, Seltzer, Michael L. |
|---|---|
| Rok vydání: | 2020 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of access to the full sequence and the quadratically growing computational cost concerning the sequence length. These characteristics pose challenges, especially for low-latency scenarios, where the system is often required to be streaming. In this paper, we build a compact and streaming speech recognition system on top of the end-to-end neural transducer architecture with attention-based modules augmented with convolution. The proposed system equips the end-to-end models with the streaming capability and reduces the large footprint from the streaming attention-based model using augmented memory. On the LibriSpeech dataset, our proposed system achieves word error rates 2.7% on test-clean and 5.8% on test-other, to our best knowledge the lowest among streaming approaches reported so far. Comment: IEEE Spoken Language Technology Workshop 2021 |
| Databáze: | arXiv |
| Externí odkaz: |
|