Search Results for author:
Found 9 papers, 1 papers with code
Listenable Maps for Audio Classifiers
Despite the impressive performance of deep learning models across diverse tasks, their complexity poses challenges for interpretation.
tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models
Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing.
Audio Editing with Non-Rigid Text Prompts
We show that the proposed editing pipeline is able to create audio edits that remain faithful to the input audio.
Posthoc Interpretation via Quantization
In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained classifiers.
Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Given the modular nature of the well-known Conv-Tasnet speech separation architecture, in this paper we consider three parameters that directly control the overall size of the model, namely: the number of residual blocks, the number of repetitions of the separation blocks and the number of channels in the depth-wise convolutions, and experimentally evaluate how they affect the speech separation performance.
XiNet: Efficient Neural Networks for tinyML
The recent interest in the edge-to-cloud continuum paradigm has emphasized the need for simple and scalable architectures to deliver optimal performance on computationally constrained devices.
Low-complexity acoustic scene classification in DCASE 2022 Challenge
The provided baseline system is a convolutional neural network which employs post-training quantization of parameters, resulting in 46. 5 K parameters, and 29. 23 million multiply-and-accumulate operations (MMACs).
PhiNets: a scalable backbone for low-power AI at the edge
In the Internet of Things era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing the intelligence from the cloud to the edge has become a necessity.
Enabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoT
Therefore, domain-specific pipelines are usually delivered in order to exploit the full potential of these cameras.
