Possible advisorsa guess from early papers, not confirmed

• Suranga Chandima Nanayakkara

  Possible advisor · last author on 4 of their early first-author papers, 2024–2025

  Suggested from co-authorship

Is this you? Claim this profile to confirm or dismiss it.

• Sound Designer-Generative AI Interactions: Towards Designing Creative Support Tools for Professional Sound Designers

  Purnima Kamath, Fabio Morreale, Priambudi Lintang Bagaskara, Yize Wei, Suranga Chandima Nanayakkara

  CHI Conference on Human Factors in Computing Systems · 2024

  Insight into sound designers’ expectations of generative AI and opportunities to situate generative AI-based tools within the design process are provided.

  47
• Sound Model Factory: An Integrated System Architecture for Generative Audio Modelling

  Lonce L. Wyse, Purnima Kamath, Chitralekha Gupta

  Lecture notes in computer science · 2022

  A new system for data-driven audio sound model design built around two neural network architectures, a Generative Adversarial Network and a Recurrent Neural Network, that takes advantage of the unique characteristics of each to achieve the system objectives that neither is capable of addressing alone.

  12
• MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models

  Purnima Kamath, Chitralekha Gupta, Suranga Chandima Nanayakkara

  IEEE International Conference on Acoustics Speech and Signal Processing · 2025

  This paper proposes MorphFader, a controllable method for morphing sounds generated by disparate prompts using text-to-audio models that can create smooth morphs between sounds generated by different text prompts.

  10
• Towards Controllable Audio Texture Morphing

  Chitralekha Gupta, Purnima Kamath, Yize Wei, Zhuoyao Li, Suranga Chandima Nanayakkara, Lonce L. Wyse

  IEEE International Conference on Acoustics Speech and Signal Processing · 2023

  A data-driven approach to train a Generative Adversarial Network conditioned on "soft-labels" distilled from the penultimate layer of an audio classifier trained on a target set of audio texture classes demonstrates that interpolation between conditions or control vectors provide smooth morphing between the generated audio textures.

  8
• Example-Based Framework for Perceptually Guided Audio Texture Generation

  Purnima Kamath, Chitralekha Gupta, Lonce L. Wyse, Suranga Chandima Nanayakkara

  IEEE/ACM Transactions on Audio Speech and Language Processing · 2024

  This paper develops a method for semantic control over an unconditionally trained StyleGAN in the absence of such labeled datasets, and proposes an example-based framework to determine guidance vectors for audio texture generation based on user-defined semantic attributes.

  6
• Parameter Sensitivity of Deep-Feature based Evaluation Metrics for Audio Textures

  Chitralekha Gupta, Yize Wei, Zequn Gong, Purnima Kamath, Zhuoyao Li, Lonce L. Wyse

  arXiv · 2022

  This work study and evaluate the sensitivity of existing standard metrics as well as Gram matrix and cochlear-model based metrics to control-parameter variations in audio textures across a wide range of texture and parameter types, and finds that each of the metrics is sensitive to different sets of texture-parameters types.

  6
• Evaluating Descriptive Quality of AI-Generated Audio Using Image-Schemas

  Purnima Kamath, Zhuoyao Li, Chitralekha Gupta, Kokil Jaidka, Suranga Chandima Nanayakkara, Lonce L. Wyse

  ACM International Conference on Intelligent User Interfaces (IUI) · 2023

  The use of visual metaphors of image-schema to design interfaces to evaluate AI-generated audio and the importance of framing and contextualizing a descriptive audio quality under measurement under measurement is highlighted using such constructs.

  5
• Signal Representations for Synthesizing Audio Textures with Generative Adversarial Networks

  Chitralekha Gupta, Purnima Kamath, Lonce L. Wyse

  arXiv · 2021

  2
• Sensitivity Analysis of Generative Spatial Audio Metrics: A Study on Responsiveness, Smoothness, and Symmetry

  Purnima Kamath, Adrian S. Roman, Koichi Saito, Yuki Mitsufuji, Juan Pablo Bello

  arXiv · 2026

  This work proposes a framework to analyze metric sensitivity along continuous spatial trajectories, drawing on principles of sensitivity analysis in parametric sound synthesis, and shows that FAD using localization-specific embeddings and acoustic maps yield high Responsiveness and robust Smoothness and Symmetry across conditions, while intensity vectors degrade with increasing scene complexity.

  –
• Prompt-to-Touch: Towards Enabling Automatic Haptic Effect Generation from Text Prompts Using Text-to-Audio Models

  Moritz Alexander Messerschmidt, Purnima Kamath, Yadeesha Weerasinghe, Suranga Chandima Nanayakkara

  ACM Transactions on Computer-Human Interaction · 2026

  The results indicate that the Prompt-to-Touch pipeline can generate effects to enhance immersive multimedia experiences, abstract desktop/XR interactions, and social communication applications, and still reveal significant potential for further improvement.

  –