Papers › End-to-end speech recognition using lattice-free MMI

End-to-end speech recognition using lattice-free MMI

6 Sep 2018Interspeech 2018 2018 9archive 2025-07-28

Hossein Hadian, Hossein Sameti, Daniel Povey, Sanjeev Khudanpur

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 relative reduction in word error rates on different large vocabulary tasks while using significantly smaller models.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Speech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition Switchboard (300hr) End-to-end LF-MMI Word Error Rate (WER) 9.3 #1 of 1 Archive leaderboard report
Speech Recognition WSJ eval92 End-to-end LF-MMI Word Error Rate (WER) 3.0 #7 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections