Robust Knowledge Distillation from RNN-T Models with Noisy Training Labels Using Full-Sum Loss - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar, Bhuvana Ramabhadran. Robust Knowledge Distillation from RNN-T Models with Noisy Training Labels Using Full-Sum Loss. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]

This author has not been identified. Look up 'Mohammad Zeineldeen' in GoogleThis author has not been identified. Look up 'Kartik Audhkhasi' in GoogleThis author has not been identified. Look up 'Murali Karthick Baskar' in GoogleThis author has not been identified. Look up 'Bhuvana Ramabhadran' in Google

runs on WebDSL