3 papers
cs.CL2022
Modular Hybrid Autoregressive Transducer
Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar +10
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 (…
cs.SD2022
Non-Parallel Voice Conversion for ASR Augmentation
Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran +4
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…
eess.AS2020
Language-agnostic Multilingual Modeling
Arindrima Datta, Bhuvana Ramabhadran, Jesse Emond +2
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 shari…