On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech

June 09, 2020 Β· Declared Dead Β· πŸ› Workshop on Time-Delay Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors BalΓ‘zs TarjΓ‘n, GyΓΆrgy SzaszΓ‘k, Tibor FegyΓ³, PΓ©ter Mihajlik arXiv ID 2006.05129 Category eess.AS: Audio & Speech Cross-listed cs.CL, cs.SD Citations 2 Venue Workshop on Time-Delay Systems Last Checked 3 months ago
Abstract
Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-gram Language Models (BNLM) partly or entirely. The reason for this are the high cost and complexity of training and using neural language models, mostly possible by adding a second decoding pass (rescoring). In our recent work we have significantly improved the online performance of a conversational speech transcription system by transferring knowledge from a Recurrent Neural Network Language Model (RNNLM) to the single pass BNLM with text generation based data augmentation. In the present paper we analyze the amount of transferable knowledge and demonstrate that the neural augmented LM (RNN-BNLM) can help to capture almost 50% of the knowledge of the RNNLM yet by dropping the second decoding pass and making the system real-time capable. We also systematically compare word and subword LMs and show that subword-based neural text augmentation can be especially beneficial in under-resourced conditions. In addition, we show that using the RNN-BNLM in the first pass followed by a neural second pass, offline ASR results can be even significantly improved.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Audio & Speech

Died the same way β€” πŸ‘» Ghosted