Skip to content

LF-MMI

Johns Hopkins UniversityCornell UniversitySpeech recognition (ASR)

LF-MMI is a Speech recognition (ASR) model from Johns Hopkins University,Cornell University released in 2016 with 16600000.0 parameters.

About LF-MMI

In this paper we describe a method to perform sequencediscriminative training of neural network acoustic models without the need for frame-level cross-entropy pre-training. We use the lattice-free version of the maximum mutual information (MMI) crite

Details

Provider
Johns Hopkins University,Cornell University
Task
Speech recognition (ASR)
Parameters
16600000.0
Released
2016-09-08
Open weights
No
View model source

Explore

FAQ