Structured State Space Decoder for Speech Recognition and Synthesis

no code implementations • 31 Oct 2022 • Koichi Miyazaki, Masato Murata, Tomoki Koriyama

Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e. g., Transformer and Conformer), which are replacing conventional recurrent neural networks.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1