Analysis of Automatic Speech Recognition Methods

This paper outlines structures of different automatic speech recognition systems, hybrid and end-to-end, pros and cons for each of them, including the comparison of training data and computational resources requirements. Three main approaches to speech recognition are considered: hybrid Hidden Markov Model – Deep Neural Network, end-to-end Connectionist Temporal Classification and Sequence-to-Sequence. The Listen, Attend, and Spell approach is chosen as an example for the Sequence-to-Sequence model