End-to-End Speech Recognition Models

End-to-End Speech Recognition Models

For the past few decades, the bane of Automatic Speech Recognition (ASR) systems have been phonemes and Hidden Markov Models (HMMs). HMMs assume conditional indepen-dence between observations, and the reliance on explicit phonetic representations requires expensive handcrafted pronunciation dictiona...

Full description

Bibliographic Details
Main Author: Chan, William
Format: Others
Published: Research Showcase @ CMU 2016
Subjects:
Artificial Intelligence
Automatic Speech Recognition
Deep Learning
Machine Learning
Neural Networks
Online Access:http://repository.cmu.edu/dissertations/723
http://repository.cmu.edu/cgi/viewcontent.cgi?article=1762&context=dissertations

Internet

http://repository.cmu.edu/dissertations/723
http://repository.cmu.edu/cgi/viewcontent.cgi?article=1762&context=dissertations

Similar Items