Name
Abstract | ||
|---|---|---|
We present a simple and efficient auxiliary loss function for automatic speech recognition (ASR) based on the connectionist temporal classification (CTC) objective. The proposed objective, an intermediate CTC loss, is attached to an intermediate layer in the CTC encoder network. This intermediate CTC loss well regularizes CTC training and improves the performance requiring only small modification of the code and small and no overhead during training and inference, respectively. In addition, we propose to combine this intermediate CTC loss with stochastic depth training, and apply this combination to a recently proposed Conformer network. We evaluate the proposed method on various corpora, reaching word error rate (WER) 9.9% on the WSJ corpus and character error rate (CER) 5.2% on the AISHELL-1 corpus respectively, based on CTC greedy search without a language model. Especially, the AISHELL-1 task is comparable to other state-of-the-art ASR systems based on autoregressive decoder with beam search. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414594 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
end-to-end speech recognition, connectionist temporal classification, multitask learning, non-autoregressive | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jaesong Lee | 1 | 1 | 0.69 |
| Shinji Watanabe | 2 | 1158 | 139.38 |