TR02: State dependent oracle masks for improved dynamical features
J. F. Gemmeke, B. Cranen
TL;DR
This paper introduces a state-dependent mask estimation technique that significantly improves speech recognition accuracy over traditional SNR-based oracle masks on the AURORA-2 digit recognition task.
Contribution
The paper presents a novel state-dependent mask estimation method that enhances the quality of dynamical features for speech recognition.
Findings
Recognition accuracy improved with state-dependent masks
Outperforms classical SNR-based oracle masks
Effective on the AURORA-2 dataset
Abstract
Using the AURORA-2 digit recognition task, we show that recognition accuracies obtained with classical, SNR based oracle masks can be substantially improved by using a state-dependent mask estimation technique.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech and Audio Processing · Digital Media Forensic Detection · Image and Signal Denoising Methods