Lessons from Building Acoustic Models with a Million Hours of Speech.

Sree Hari Krishnan Parthasarathi Nikko Strom

Published in: ICASSP (2019)

Keyphrases

acoustic models
speech recognition
automatic speech recognition
speech recognizer
broadcast news
hidden markov models
speaker independent
speech signal
discriminative training
speech recognition systems
feature selection
bayesian networks
pattern recognition
feature vectors
noisy environments
spoken language