Skip to Main content Skip to Navigation
Conference papers

Semi-supervised triplet loss based learning of ambient audio embeddings

Nicolas Turpault 1 Romain Serizel 1 Emmanuel Vincent 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Deep neural networks are particularly useful to learn relevant repre-sentations from data. Recent studies have demonstrated the poten-tial of unsupervised representation learning for ambient sound anal-ysis using various flavors of the triplet loss. They have comparedthis approach to supervised learning. However, in real situations,it is common to have a small labeled dataset and a large unlabeledone. In this paper, we combine unsupervised and supervised tripletloss based learning into a semi-supervised representation learningapproach. We propose two flavors of this approach, whereby thepositive samples for those triplets whose anchors are unlabeled areobtained either by applying a transformation to the anchor, or byselecting the nearest sample in the training set. We compare ourapproach to supervised and unsupervised representation learning aswell as the ratio between the amount of labeled and unlabeled data.We evaluate all the above approaches on an audio tagging task usingthe DCASE 2018 Task 4 dataset, and we show the impact of thisratio on the tagging performance.
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02025824
Contributor : Nicolas Turpault <>
Submitted on : Friday, February 22, 2019 - 11:26:01 AM
Last modification on : Monday, May 4, 2020 - 11:40:14 AM
Document(s) archivé(s) le : Thursday, May 23, 2019 - 2:41:26 PM

File

ssl_triplet.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02025824, version 1

Citation

Nicolas Turpault, Romain Serizel, Emmanuel Vincent. Semi-supervised triplet loss based learning of ambient audio embeddings. ICASSP 2019, May 2019, Brighton, United Kingdom. ⟨hal-02025824⟩

Share

Metrics

Record views

322

Files downloads

984