Utilizing Domain Knowledge in End-to-End Audio Processing

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Abstract

End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used log-scaled mel-spectrogram transformation. Secondly, we demonstrate that upon initializing the first layers of an end-to-end CNN classifier with the learned transformation, convergence and performance on the ESC-50 environmental sound classification dataset are similar to a CNN-based model trained on the highly pre-processed log-scaled mel-spectrogram features.
Luk

Detaljer

End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used log-scaled mel-spectrogram transformation. Secondly, we demonstrate that upon initializing the first layers of an end-to-end CNN classifier with the learned transformation, convergence and performance on the ESC-50 environmental sound classification dataset are similar to a CNN-based model trained on the highly pre-processed log-scaled mel-spectrogram features.
OriginalsprogEngelsk
TitelWorkshop Machine Learning for Audio Signal Processing at NIPS 2017 (ML4Audio@NIPS17)
Publikationsdatodec. 2017
StatusUdgivet - dec. 2017
PublikationsartForskning
Peer reviewJa
BegivenhedConference and Workshop on Neural Information Processing Systems (NIPS): Machine Learning for Audio Signal Processing - Long Beach Convention & Entertainment Center, Long Beach, USA
Varighed: 8 dec. 20178 dec. 2017
https://nips.cc/Conferences/2017/Schedule?showEvent=8790

Konference

KonferenceConference and Workshop on Neural Information Processing Systems (NIPS)
LokationLong Beach Convention & Entertainment Center
LandUSA
ByLong Beach
Periode08/12/201708/12/2017
Internetadresse

Kort

ID: 267675737