BYOL for Audio: Exploring Pre-Trained General-Purpose Audio Representations

Exploring Features for Audio

Tahakum: A Multi-Purpose Audio Control Framework

We present “Tahakum”, an open source, extensible collection of software tools designed to enhance workflow on multichannel audio systems within complex multi-functional research and development environments. Tahakum aims to provide critical functionality required across a broad spectrum of audio systems usage scenarios, while at the same time remaining sufficiently open as to easily support mod...

Feature Representations for Neuromorphic Audio Spike Streams

Event-driven neuromorphic spiking sensors such as the silicon retina and the silicon cochlea encode the external sensory stimuli as asynchronous streams of spikes across different channels or pixels. Combining state-of-art deep neural networks with the asynchronous outputs of these sensors has produced encouraging results on some datasets but remains challenging. While the lack of effective spi...

Representations of ambient audio for the Deaf

Watermarking parametric representations for synthetic audio

This paper proposes to watermark parametric representations for synthetic audio. Our watermark system combines quantization index modulation at the encoder and maximum likelihood parameter estimation at the decoder. To guarantee error-free data hiding under expected types of attacks, knowledge of Fisher information and Cramér-Rao bounds is applied to the system design. Experiments show that, me...