Loading...
Search for:
context-dependent-modeling
0.005 seconds
End-to-end speech recognition using lattice-free MMI
, Article 19th Annual Conference of the International Speech Communication, INTERSPEECH 2018, 2 September 2018 through 6 September 2018 ; Volume 2018-September , 2018 , Pages 12-16 ; 2308457X (ISSN) ; Sameti, H ; Povey, D ; Khudanpur, S ; Sharif University of Technology
International Speech Communication Association
2018
Abstract
We present our work on end-to-end training of acoustic models using the lattice-free maximum mutual information (LF-MMI) objective function in the context of hidden Markov models. By end-to-end training, we mean flat-start training of a single DNN in one stage without using any previously trained models, forced alignments, or building state-tying decision trees. We use full biphones to enable context-dependent modeling without trees, and show that our end-to-end LF-MMI approach can achieve comparable results to regular LF-MMI on well-known large vocabulary tasks. We also compare with other end-to-end methods such as CTC in character-based and lexicon-free settings and show 5 to 25 percent...