Neuralogram: A Deep Neural Network Based Representation for Audio Signals
arXiv:1904.05073
Abstract
We propose the Neuralogram -- a deep neural network based representation for understanding audio signals which, as the name suggests, transforms an audio signal to a dense, compact representation based upon embeddings learned via a neural architecture. Through a series of probing signals, we show how our representation can encapsulate pitch, timbre and rhythm-based information, and other attributes. This representation suggests a method for revealing meaningful relationships in arbitrarily long audio signals that are not readily represented by existing algorithms. This has the potential for numerous applications in audio understanding, music recommendation, meta-data extraction to name a few.
Submitted to DAFx 2019, the 22nd International Conference on Digital Audio Effects, Birmingham, United Kingdom
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distributed Representations of Words and Phrases and their Compositionality
- VoxCeleb2: Deep Speaker Recognition
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- A Neural Representation of Sketch Drawings
- Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
- Neural Style Transfer for Audio Spectograms
- Learning Multiscale Features Directly From Waveforms
- Deep Learning for Music
- Audio-Linguistic Embeddings for Spoken Sentences