Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 6783 - 6787
• Main Authors: Shi, Yangyang, Wang, Yongqiang, Wu, Chunyang, Yeh, Ching-Feng, Chan, Julian, Zhang, Frank, Le, Duc, Seltzer, Mike
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2021
• Subjects: Acoustics; Computational modeling; Emformer; Low Latency; Memory management; Signal processing; Speech recognition; Training; Transducers; Transformer

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention's computation complexity. A cache mechanism saves the computation for the ke...