Comparison Of Lattice-free And Lattice-based Sequence Discriminative Training Criteria For LVCSR
2019 · Wilfried Michel, Ralf Schlüter, Hermann Ney
Abstract
Sequence discriminative training criteria have long been a standard tool in automatic speech recognition for improving the performance of acoustic models over their maximum likelihood / cross entropy trained counterparts. While previously a lattice approximation of the search space has been necessary to reduce computational complexity, recently proposed methods use other approximations to dispense of the need for the computationally expensive step of separate lattice creation. In this work we present a memory efficient implementation of the forward-backward computation that allows us to use uni-gram word-level language models in the denominator calculation while still doing a full summation on GPU. This allows for a direct comparison of lattice-based and lattice-free sequence discriminative training criteria such as MMI and sMBR, both using the same language model during training. We compared performance, speed of convergence, and stability on large vocabulary continuous speech rec
Authors
(none)
Tags
Stats
Related papers
- A Comparison Of Lattice-free Discriminative Training Criteria For Purely Sequence-trained Neural Network Acoustic Models (2018)4.52
- Consistent Training And Decoding For End-to-end Speech Recognition Using Lattice-free MMI (2021)8.35
- Lattice Rescoring Strategies For Long Short Term Memory Language Models In Speech Recognition (2017)9.76
- Linguistic Search Optimization For Deep Learning Based LVCSR (2018)0.00
- Lattice-based Lightly-supervised Acoustic Model Training (2019)0.00
- On Lattice-free Boosted MMI Training Of HMM And Ctc-based Full-context ASR Models (2021)7.81
- On The Relation Between Internal Language Model And Sequence Discriminative Training For Neural Transducers (2023)0.00
- Voice Trigger Detection From LVCSR Hypothesis Lattices Using Bidirectional Lattice Recurrent Neural Networks (2020)6.77