Jesse Emond
YOU?
Author Swipe
View article: Language-Agnostic Multilingual Modeling
Language-Agnostic Multilingual Modeling Open
Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the…
View article: Modular Hybrid Autoregressive Transducer
Modular Hybrid Autoregressive Transducer Open
Text-only adaptation of a transducer model remains challenging for end-to-end speech recognition since the transducer has no clearly separated acoustic model (AM), language model (LM) or blank model. In this work, we propose a modular hybr…
View article: Non-Parallel Voice Conversion for ASR Augmentation
Non-Parallel Voice Conversion for ASR Augmentation Open
Automatic speech recognition (ASR) needs to be robust to speaker differences. Voice Conversion (VC) modifies speaker characteristics of input speech. This is an attractive feature for ASR data augmentation. In this paper, we demonstrate th…