Audio Scene Classification with Deep Recurrent Neural Networks

Abstract

We introduce in this work an efficient approach for audio scene classification using deep recurrent neural networks. An audio scene is firstly transformed into a sequence of high-level label tree embedding feature vectors. The vector sequence is then divided into multiple subsequences on which a deep GRU-based recurrent neural network is trained for sequence-to-label classification. The global predicted label for the entire sequence is finally obtained via aggregation of subsequence classification outputs. We will show that our approach obtains an F1-score of 97.7% on the LITIS Rouen dataset, which is the largest dataset publicly available for the task. Compared to the best previously reported result on the dataset, our approach is able to reduce the relative classification error by 35.3%.
OriginalspracheEnglisch
TitelProc. 18th Annual Conf. of the Intl. Speech Communication Association (INTERSPEECH)
Seitenumfang5
Band 2017-August
ErscheinungsortStockholm, Sweden
Herausgeber (Verlag) International Speech Communication Association (ISCA)
Erscheinungsdatum01.08.2017
Seiten3043-3047
DOIs
PublikationsstatusVeröffentlicht - 01.08.2017
Veranstaltung18th Annual Conference of the International Speech Communication Association - Stockholm, Schweden
Dauer: 20.08.201724.08.2017
Konferenznummer: 132696

Fingerprint

Untersuchen Sie die Forschungsthemen von „Audio Scene Classification with Deep Recurrent Neural Networks“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren