CRF-based Single-stage Acoustic Modeling with CTC Topology
In this paper, we develop conditional random field (CRF) based single-stage (SS) acoustic modeling with connectionist temporal classification (CTC) inspired state topology, which is called CTC-CRF for short. CTC-CRF is conceptually simple, which basically implements a CRF layer on top of features generated by the bottom neural network with the special state topology. Like SS-LF-MMI (lattice-free maximum-mutual-information), CTC-CRFs can be trained from scratch (flat-start), eliminating GMM-HMM pre-training and tree-building. Evaluation experiments are conducted on the WSJ, Switchboard and Librispeech datasets. In a head-to-head comparison, the CTC-CRF model using simple Bidirectional LSTMs consistently outperforms the strong SS-LF-MMI, across all the three benchmarking datasets and in both cases of mono-phones and mono-chars. Additionally, CTC-CRFs avoid some ad-hoc operation in SS-LF-MMI.
PDF AbstractCode
Datasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Speech Recognition | LibriSpeech test-clean | CTC-CRF 4gram-LM | Word Error Rate (WER) | 4.09 | # 44 | |
Speech Recognition | LibriSpeech test-other | CTC-CRF 4gram-LM | Word Error Rate (WER) | 10.65 | # 42 | |
Speech Recognition | WSJ dev93 | Convolutional Speech Recognition | Word Error Rate (WER) | 6.23 | # 3 | |
Speech Recognition | WSJ eval92 | CTC-CRF 4gram-LM | Word Error Rate (WER) | 3.79 | # 14 | |
Speech Recognition | WSJ eval93 | CTC-CRF 4gram-LM | Word Error Rate (WER) | 6.23 | # 2 |