· 2017
CNN architectures for large-scale audio classification
- 2,478citations
- 2017year
Short summary
Convolutional Neural Networks (CNNs) adapted from image classification achieve strong performance on a massive audio classification task involving 70 million training videos.
AI-generated from the title and abstract; the full text is not read.
Key points
- CNNs originally designed for image classification are effective for large-scale audio classification.
- Tested architectures include DNNs, AlexNet, VGG, Inception, and ResNet.
- Performance improves with larger training sets and label vocabularies, up to a point.
- Embeddings from CNN classifiers outperform raw features on the Audio Set AED task.
AI-generated from the title and abstract; the full text is not read.
Abstract
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 video-level labels. We examine fully connected Deep Neural Networks (DNNs), AlexNet [1], VGG [2], Inception [3], and ResNet [4]. We investigate varying the size of both training set and label vocabulary, finding that analogs of the CNNs used in image classification do well on our audio classification task, and larger training and label sets help up to a point. A model using embeddings from these classifiers does much better than raw features on the Audio Set [5] Acoustic Event Detection (AED) classification task.
The authors' abstract, as published at the source., 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science