Study on continuous speech recognition based on bottleneck features for Lhasa-Tibetan dialect

DOI10.13209/J.0479-8023.2017.154MaRDI QIDQ4687727zbMATH OpenWikidataFDO

Authors Nan Zhou, Yue Zhao, Y.-Q. Li, Xiao-Na Xu, Lamu Caiwang, Licheng Wu

Publication date 22 October 2018

Full work available at URL https://doi.org/10.13209/J.0479-8023.2017.154

zbMATH Keywords

bottleneck featurescontinuous speech recognitiondeep neural networkLhasa-Tibetan dialect

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Natural language processing (68T50)

Recommendations

• Continuous speech recognition by convolutional neural networks
• A continuous speech recognition method using dependent feature transformation and combination of subspace region
• AP clustering analysis of Lhasa dialect speech feature vectors
• Advances in Neural Networks – ISNN 2005
• Kernel approximation methods for speech recognition

Cited in

(3)

• English speech recognition based on deep learning with multiple features
• A continuous speech recognition method using dependent feature transformation and combination of subspace region
• AP clustering analysis of Lhasa dialect speech feature vectors

This page was built for publication: Study on continuous speech recognition based on bottleneck features for Lhasa-Tibetan dialect

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4687727)