The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment
arXiv:2004.00960
Abstract
We present a complete training pipeline to build a state-of-the-art hybrid HMM-based ASR system on the 2nd release of the TED-LIUM corpus. Data augmentation using SpecAugment is successfully applied to improve performance on top of our best SAT model using i-vectors. By investigating the effect of different maskings, we achieve improvements from SpecAugment on hybrid HMM models without increasing model size and training time. A subsequent sMBR training is applied to fine-tune the final acoustic model, and both LSTM and Transformer language models are trained and evaluated. Our best system achieves a 5.6% WER on the test set, which outperforms the previous state-of-the-art by 27% relative.
arXiv commentaccepted at ICASSP 2020
References in corpus (7)
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- A Comparative Study on Transformer vs RNN in Speech Applications
- Language Modeling with Deep Transformers
- A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
- The CAPIO 2017 Conversational Speech Recognition System
- On Using SpecAugment for End-to-End Speech Translation
- LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring