4 citations · 8 across the 7 of their papers we have counts for
7 papers
Sensitivity Analysis of Generative Spatial Audio Metrics: A Study on Responsiveness, Smoothness, and Symmetry
Purnima Kamath, Adrian S. Roman, Koichi Saito +2
Evaluating generative spatial audio for First-Order Ambisonics (FOA) remains challenging due to a limited understanding of how metrics respond to changes in spatial parameters such…
MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models
Purnima Kamath, Chitralekha Gupta, Suranga Nanayakkara
Sound morphing is the process of gradually and smoothly transforming one sound into another to generate novel and perceptually hybrid sounds that simultaneously resemble both. Rece…
Example-Based Framework for Perceptually Guided Audio Texture Generation
Purnima Kamath, Chitralekha Gupta, Lonce Wyse +1
Controllable generation using StyleGANs is usually achieved by training the model using labeled data. For audio textures, however, there is currently a lack of large semantically l…
Towards Controllable Audio Texture Morphing
Chitralekha Gupta, Purnima Kamath, Yize Wei +3
In this paper, we propose a data-driven approach to train a Generative Adversarial Network (GAN) conditioned on "soft-labels" distilled from the penultimate layer of an audio class…
Parameter Sensitivity of Deep-Feature based Evaluation Metrics for Audio Textures
Chitralekha Gupta, Yize Wei, Zequn Gong +3
Standard evaluation metrics such as the Inception score and Fréchet Audio Distance provide a general audio quality distance metric between the synthesized audio and reference clean…
Sound Model Factory: An Integrated System Architecture for Generative Audio Modelling
Lonce Wyse, Purnima Kamath, Chitralekha Gupta
We introduce a new system for data-driven audio sound model design built around two different neural network architectures, a Generative Adversarial Network(GAN) and a Recurrent Ne…
Signal Representations for Synthesizing Audio Textures with Generative Adversarial Networks
Chitralekha Gupta, Purnima Kamath, Lonce Wyse
Generative Adversarial Networks (GANs) currently achieve the state-of-the-art sound synthesis quality for pitched musical instruments using a 2-channel spectrogram representation c…