Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition

no code implementations • 30 Jun 2020 • Maarten Van Segbroeck, Harish Mallidih, Brian King, I-Fan Chen, Gurpreet Chadha, Roland Maas

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1