ICASSP 2021

Semi-Supervised Spoken Language Understanding Via Self-Supervised Speech And Language Model Pretraining

What'S All The Fuss About Free Universal Sound Separation Data?

Surrogate Source Model Learning For Determined Source Separation

Blind Extraction Of Moving Audio Source In A Challenging Environment Supported By Speaker Identification Via X-Vectors

Demonstration Of Quantum Circuits Learning For Spoken Commands Recognition

Dynamic Sparsity Neural Networks For Automatic Speech Recognition

Improving Prosody Modelling With Cross-Utterance Bert Embeddings For End-To-End Speech Synthesis

Rnn Transducer Models For Spoken Language Understanding

Sepnet: A Deep Separation Matrix Prediction Network For Multichannel Audio Source Separation

Bifocal Neural Asr: Exploiting Keyword Spotting For Inference Optimization

Joint Radar-Communication Prototype Implementing Spectral-Spatial Agility And Index Modulation

An Asynchronous Wfst-Based Decoder For Automatic Speech Recognition