A Novel Pyramidal-fsmn Architecture With Lattice-free MMI For Speech Recognition

Abstract

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 in different layers. 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% and 10.89% respectively on Librispeech and LDC97S62 (Switchboard 300 hours) corpora. Furthermore, Recurrent neural network language model (RNNLM) rescoring is applied and a WER of 2.97% is obtained on Librispeech.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2018a

Related papers

• Deep Feed-forward Sequential Memory Networks For Speech Synthesis (2018)5.84
• Consistent Training And Decoding For End-to-end Speech Recognition Using Lattice-free MMI (2021)8.35
• Bayesian Learning Of LF-MMI Trained Time Delay Neural Networks For Speech Recognition (2020)8.82
• DFSMN-SAN With Persistent Memory Model For Automatic Speech Recognition (2019)5.84
• Lattice Rescoring Strategies For Long Short Term Memory Language Models In Speech Recognition (2017)9.76
• Language Model Integration Based On Memory Control For Sequence To Sequence Speech Recognition (2018)2.26
• Bidirectional Quaternion Long-short Term Memory Recurrent Neural Networks For Speech Recognition (2018)9.41
• A Comparison Of Lattice-free Discriminative Training Criteria For Purely Sequence-trained Neural Network Acoustic Models (2018)4.52