Dataset balancing can hurt model performance

Autor: Moore, R. Channing, Ellis, Daniel P. W., Fonseca, Eduardo, Hershey, Shawn, Jansen, Aren, Plakal, Manoj

Publikováno v: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5

Machine learning from training data with a skewed distribution of examples per class can lead to models that favor performance on common classes at the expense of performance on rare ones. AudioSet has a very wide range of priors over its 527 sound e

Externí odkaz: http://arxiv.org/abs/2307.00079

Self-Supervised Learning from Automatically Separated Sound Scenes

Autor: Fonseca, Eduardo, Jansen, Aren, Ellis, Daniel P. W., Wisdom, Scott, Tagliasacchi, Marco, Hershey, John R., Plakal, Manoj, Hershey, Shawn, Moore, R. Channing, Serra, Xavier

Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and each other

Externí odkaz: http://arxiv.org/abs/2105.02132

Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision

Autor: Jansen, Aren, Ellis, Daniel P. W., Hershey, Shawn, Moore, R. Channing, Plakal, Manoj, Popat, Ashok C., Saurous, Rif A.

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal uns

Externí odkaz: http://arxiv.org/abs/1911.05894

CNN Architectures for Large-Scale Audio Classification

Autor: Hershey, Shawn, Chaudhuri, Sourish, Ellis, Daniel P. W., Gemmeke, Jort F., Jansen, Aren, Moore, R. Channing, Plakal, Manoj, Platt, Devin, Saurous, Rif A., Seybold, Bryan, Slaney, Malcolm, Weiss, Ron J., Wilson, Kevin

Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 vide

Externí odkaz: http://arxiv.org/abs/1609.09430

Self-Supervised Learning from Automatically Separated Sound Scenes

Autor: Eduardo Fonseca, Aren Jansen, Daniel P. W. Ellis, Scott Wisdom, Marco Tagliasacchi, John R. Hershey, Manoj Plakal, Shawn Hershey, R. Channing Moore, Xavier Serra

Comunicació presentada a 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), celebrat del 17 al 20 d'octubre de 2021 a New Paltz, Estats Units. Real-world sound scenes consist of time-varying collections of sound

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b61bcf54e52a20604b992da9fb020b48