End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition

Palaz, Dimitri; Magimai-Doss, Mathew; Collobert, Ronan

doi:10.1016/j.specom.2019.01.004

End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition

In hidden Markov model (HMM) based automatic speech recognition (ASR) system, modeling the statistical relationship between the acoustic speech signal and the HMM states that represent linguistically motivated subword units such as phonemes is a crucial step. This is typically achieved by first e…