Search

Your search keyword '"Nicolas Turpault"' showing total 8 results
Start Over Author "Nicolas Turpault" Search Limiters Full Text
8 results on '"Nicolas Turpault"'

1. Automatic Tongue Delineation from MRI Images with a Convolutional Neural Network Approach

Author

Karyna Isaieva, Yves Laprie, Nicolas Turpault, Alexis Houssard, Jacques Felblinger, and Pierre-André Vuissoz

Subjects
Electronic computers. Computer science, QA75.5-76.95, Cybernetics, Q300-390
Abstract

Tongue contour extraction from real-time magnetic resonance images is a nontrivial task due to the presence of artifacts manifesting in form of blurring or ghostly contours. In this work, we present results of automatic tongue delineation achieved by means of U-Net auto-encoder convolutional neural network. We present both intra- and inter-subject validation. We used real-time magnetic resonance images and manually annotated 1-pixel wide contours as inputs. Predicted probability maps were post-processed in order to obtain 1-pixel wide tongue contours. The results are very good and slightly outperform published results on automatic tongue segmentation.

Published
2020
Full Text
View/download PDF

2. Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes

Author

Romain Serizel, Hakan Erdogan, Justin Salamon, Nicolas Turpault, John R. Hershey, Scott Wisdom, Eduardo Fonseca, Prem Seetharaman, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Google Inc, Research at Google, Universitat Pompeu Fabra [Barcelona] (UPF), Descript, Inc., Adobe Research, Part of this work was made with the support of the French National Research Agency, in the framework of the project LEAUDS 'Learning to understand audio scenes' (ANR-18-CE23-0020) and the French region Grand-Est. High Performance Computing resources were partially provided by the EXPLOR centre hosted by the University de Lorraine., Grid'5000, ANR-18-CE23-0020,LEAUDS,Apprentissage statistique pour la compréhension de scènes audio(2018), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Sound localization, Sound (cs.SD), Reverberation, Soundscape, Computer science, Speech recognition, 02 engineering and technology, Computer Science - Sound, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Audio and Speech Processing (eess.AS), Robustness (computer science), FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, Sound (geography), synthetic soundscapes, geography, Signal processing, geography.geographical_feature_category, Event (computing), Sound event detection, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], Benchmark (computing), sound separation, 020201 artificial intelligence & image processing, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

International audience; We propose a benchmark of state-of-the-art sound event detection systems (SED). We designed synthetic evaluation sets to focus on specific sound event detection challenges. We analyze the performance of the submissions to DCASE 2021 task 4 depending on time related modifications (time position of an event and length of clips) and we study the impact of non-target sound events and reverberation. We show that the localization in time of sound events is still a problem for SED systems. We also show that reverberation and non-target sound events are severely degrading the performance of the SED systems. In the latter case, sound separation seems like a promising solution.

Published
2020
Full Text
View/download PDF

3. Improving Sound Event Detection Metrics: Insights from DCASE 2020

Author

Francesco Tuveri, Sacha Krstulovic, Cagdas Bilen, Romain Serizel, Juan Azcarreta, Giacomo Ferroni, Nicolas Turpault, Audio Analytic, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), UL/INRIA’s work for this article was partly supported by the French National Research Agency (project LEAUDS 'Learning to under-stand audioscenes' ANR-18-CE23-0020) and by the French region Grand-Est., Grid'5000, and ANR-18-CE23-0020,LEAUDS,Apprentissage statistique pour la compréhension de scènes audio(2018)

Subjects
FOS: Computer and information sciences, Sound (cs.SD), Dependency (UML), Computer science, 02 engineering and technology, computer.software_genre, Computer Science - Sound, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Audio and Speech Processing (eess.AS), Robustness (computer science), FOS: Electrical engineering, electronic engineering, information engineering, 0202 electrical engineering, electronic engineering, information engineering, Event (probability theory), Operating point, Signal processing, Intersection (set theory), Sound detection, segment vs event criteria, sound event detection, evaluation metrics, Ranking, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 020201 artificial intelligence & image processing, Data mining, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, computer, polyphonic sound detection score, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

International audience; The ranking of sound event detection (SED) systems may be biased by assumptions inherent to evaluation criteria and to the choice of an operating point. This paper compares conventional event-based and segment-based criteria against the Polyphonic Sound Detection Score (PSDS)'s intersection-based criterion, over a selection of systems from DCASE 2020 Challenge Task 4. It shows that, by relying on collars , the conventional event-based criterion introduces different strictness levels depending on the length of the sound events, and that the segment-based criterion may lack precision and be application dependent. Alternatively, PSDS's intersection-based criterion overcomes the dependency of the evaluation on sound event duration and provides robustness to labelling subjectivity, by allowing valid detections of interrupted events. Furthermore, PSDS enhances the comparison of SED systems by measuring sound event modelling performance independently from the systems' operating points.

Published
2020
Full Text
View/download PDF

4. Automatic Tongue Delineation from MRI Images with a Convolutional Neural Network Approach

Author

Alexis Houssard, Yves Laprie, Jacques Felblinger, Pierre-André Vuissoz, Nicolas Turpault, Karyna Isaieva, Imagerie Adaptative Diagnostique et Interventionnelle (IADI), Université de Lorraine (UL)-Institut National de la Santé et de la Recherche Médicale (INSERM), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Centre d'Investigation Clinique - Innovation Technologique [Nancy] (CIC-IT), Centre d'investigation clinique [Nancy] (CIC), Université de Lorraine (UL)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Institut National de la Santé et de la Recherche Médicale (INSERM), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL), and Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL)-Centre Hospitalier Régional Universitaire de Nancy (CHRU Nancy)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL)

Subjects
0209 industrial biotechnology, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Convolutional neural network, Task (project management), Mri image, 020901 industrial engineering & automation, Artificial Intelligence, Tongue, 0202 electrical engineering, electronic engineering, information engineering, medicine, Computer vision, [INFO]Computer Science [cs], ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS, medicine.diagnostic_test, business.industry, Magnetic resonance imaging, medicine.anatomical_structure, Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Tongue contour extraction from real-time magnetic resonance images is a nontrivial task due to the presence of artifacts manifesting in form of blurring or ghostly contours. In this work, we present results of automatic tongue delineation achieved by means of U-Net auto-encoder convolutional neural network. We present both intra- and inter-subject validation. We used real-time magnetic resonance images and manually annotated 1-pixel wide contours as inputs. Predicted probability maps were post-processed in order to obtain 1-pixel wide tongue contours. The results are very good and slightly outperform published results on automatic tongue segmentation.

Published
2020
Full Text
View/download PDF

5. Sound event detection in synthetic domestic environments

Author

Romain Serizel, Nicolas Turpault, Justin Salamon, Ankit Shah, Serizel, Romain, APPEL À PROJETS GÉNÉRIQUE 2018 - Apprentissage statistique pour la compréhension de scènes audio - - LEAUDS2018 - ANR-18-CE23-0020 - AAPG2018 - VALID, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Language Technologies Institute [Pittsburgh] (LTI), Carnegie Mellon University [Pittsburgh] (CMU), Adobe Research, Grid'5000, ANR-18-CE23-0020,LEAUDS,LEARNING TO UNDERSTAND AUDIO SCENES(2018), ANR-18-CE23-0020,LEAUDS,Apprentissage statistique pour la compréhension de scènes audio(2018), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)

Subjects
semi-supervised learning, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Soundscape, Computer science, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, 02 engineering and technology, 030204 cardiovascular system & hematology, Machine learning, computer.software_genre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Impact model, 0202 electrical engineering, electronic engineering, information engineering, Index Terms-Sound event detection, business.industry, 020206 networking & telecommunications, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], synthetic data, Sound event detection, weakly labeled data, Artificial intelligence, business, computer
Abstract

International audience; We present a comparative analysis of the performance of state-of-the-art sound event detection systems. In particular, we study the robustness of the systems to noise and signal degradation, which is known to impact model generalization. Our analysis is based on the results of task 4 of the DCASE 2019 challenge, where submitted systems were evaluated on, in addition to real-world recordings, a series of synthetic soundscapes that allow us to carefully control for different soundscape characteristics. Our results show that while overall systems exhibit significant improvements compared to previous work, they still suffer from biases that could prevent them from generalizing to real-world scenarios.

Published
2020

6. What's All the FUSS About Free Universal Sound Separation Data?

Author

Romain Serizel, Prem Seetharaman, Justin Salamon, Daniel P. W. Ellis, John R. Hershey, Scott Wisdom, Eduardo Fonseca, Nicolas Turpault, Hakan Erdogan, Google Inc, Research at Google, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Universitat Pompeu Fabra [Barcelona] (UPF), Adobe Research, Descript, Inc., and ANR-18-CE23-0020,LEAUDS,Apprentissage statistique pour la compréhension de scènes audio(2018)

Subjects
FOS: Computer and information sciences, Reverberation, Sound (cs.SD), open-source datasets, Computer science, Sound separation, Separation (aeronautics), 02 engineering and technology, Impulse (physics), Computer Science - Sound, Data modeling, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Audio and Speech Processing (eess.AS), 0202 electrical engineering, electronic engineering, information engineering, Open domain, FOS: Electrical engineering, electronic engineering, information engineering, business.industry, Deep learning, deep learning, 020206 networking & telecommunications, Universal sound separation, variable source sep- aration, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 020201 artificial intelligence & image processing, Artificial intelligence, Variable number, business, Algorithm, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

International audience; We introduce the Free Universal Sound Separation (FUSS) dataset, a new corpus for experiments in separating mixtures of an unknown number of sounds from an open domain of sound types. The dataset consists of 23 hours of single-source audio data drawn from 357 classes, which are used to create mixtures of one to four sources. To simulate reverberation, an acoustic room simulator is used to generate impulse responses of box shaped rooms with frequency-dependent reflective walls. Additional open-source data augmentation tools are also provided to produce new mixtures with different combinations of sources and room simulations. Finally, we introduce an open-source baseline separation model, based on an improved time-domain convolutional network (TDCN++), that can separate a variable number of sources in a mixture. This model achieves 9.8 dB of scale-invariant signal-to-noise ratio improvement (SI-SNRi) on mixtures with two to four sources, while reconstructing single-source inputs with 35.5 dB absolute SI-SNR. We hope this dataset will lower the barrier to new research and allow for fast iteration and application of novel techniques from other machine learning domains to the sound separation challenge.

Published
2020
Full Text
View/download PDF

7. Sound event detection in domestic environments with weakly labeled data and soundscape synthesis

Author

Ankit Shah, Justin Salamon, Nicolas Turpault, Romain Serizel, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Language Technologies Institute [Pittsburgh] (LTI), Carnegie Mellon University [Pittsburgh] (CMU), Adobe Research, Grid'5000, Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Soundscape, Synthetic data, Computer science, 02 engineering and technology, Semi-supervised learning, Machine learning, computer.software_genre, Task (project management), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 030507 speech-language pathology & audiology, 03 medical and health sciences, Domestic environment, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Weakly labeled data, business.industry, 020206 networking & telecommunications, Sound event detection, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], Labeled data, Artificial intelligence, 0305 other medical science, business, computer
Abstract

International audience; This paper presents Task 4 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and provides a first analysis of the challenge results. The task is a followup to Task 4 of DCASE 2018, and involves training systems for large-scale detection of sound events using a combination of weakly labeled data, i.e. training labels without time boundaries, and strongly-labeled synthesized data. The paper introduces Domestic Environment Sound Event Detection (DESED) dataset mixing a part of last year dataset and an additional synthetic, strongly labeled, dataset provided this year that we’ll describe more in detail. We also report the performance of the submitted systems on the official evaluation (test) and development sets as well as several additional datasets. The best systems from this year outperform last year’s winning system by about 10% points in terms of F-measure.

Published
2019

8. Semi-supervised triplet loss based learning of ambient audio embeddings

Author

Nicolas Turpault, Emmanuel Vincent, Romain Serizel, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Région Grand Est., Grid'5000, ANR-18-CE23-0020,LEAUDS,Apprentissage statistique pour la compréhension de scènes audio(2018), Turpault, Nicolas, and APPEL À PROJETS GÉNÉRIQUE 2018 - Apprentissage statistique pour la compréhension de scènes audio - - LEAUDS2018 - ANR-18-CE23-0020 - AAPG2018 - VALID

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer Science::Machine Learning, triplet loss, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer science, Sample (statistics), Index Terms-weak labels, 02 engineering and technology, Semi-supervised learning, 010501 environmental sciences, 01 natural sciences, Task (project management), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Statistics::Machine Learning, audio tagging, Triplet loss, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, 0105 earth and related environmental sciences, Training set, prototypical network, business.industry, Supervised learning, Pattern recognition, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], Transformation (function), ComputingMethodologies_PATTERNRECOGNITION, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], 020201 artificial intelligence & image processing, Artificial intelligence, audio embedding, business, Feature learning
Abstract

International audience; 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.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results