Streaming Simultaneous Speech Translation with Augmented Memory Transformer

Mohammad Javad Dousti
Mohammad Javad Dousti
Juan Pino
Juan Pino
Cited by: 0|Views8

Abstract:

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence and the computational cost grows quadratically with the length of the input sequence. Nevertheless...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments