A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition

10/26/2018
by   Xuerui Yang, et al.
0

Deep Feedforward Sequential Memory Network (DFSMN) has shown superior performance on speech recognition tasks. Based on this work, we propose a novel network architecture which introduces pyramidal memory structure to represent various context information. Additionally, res-CNN layers are added in the front to extract more sophisticated features as well. Together with lattice-free maximum mutual information (LF-MMI) and cross entropy (CE) joint training criteria, experimental results show that this approach achieves word error rates (WERs) of 3.62 Switchboard corpora. Furthermore, Recurrent neural network language model (RNNLM) rescoring is applied and a WER of above 1 obtained.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/07/2022

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers

Recently, RNN-Transducers have achieved remarkable results on various au...
research
10/17/2022

A Treatise On FST Lattice Based MMI Training

Maximum mutual information (MMI) has become one of the two de facto meth...
research
07/01/2019

Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR

Sequence discriminative training criteria have long been a standard tool...
research
08/18/2017

Future Word Contexts in Neural Network Language Models

Recently, bidirectional recurrent network language models (bi-RNNLMs) ha...
research
03/04/2018

Deep-FSMN for Large Vocabulary Continuous Speech Recognition

In this paper, we present an improved feedforward sequential memory netw...
research
11/08/2018

A Comparison of Lattice-free Discriminative Training Criteria for Purely Sequence-Trained Neural Network Acoustic Models

In this work, three lattice-free (LF) discriminative training criteria f...
research
03/25/2022

Chain-based Discriminative Autoencoders for Speech Recognition

In our previous work, we proposed a discriminative autoencoder (DcAE) fo...

Please sign up or login with your details

Forgot password? Click here to reset