3 papers
cs.SD2026
Multichannel Audio Quality Assessment: Extending Pretrained Perceptual Models to Spatial Audio
Gouthaman KV, Shiv Gehlot, Vishnu Raj +2
Accurate perceptual quality assessment is essential for evaluating and optimizing spatial audio, where perceived quality depends on both signal fidelity and inter-channel spatial r…
eess.AS2025
Enhanced Generative Machine Listener
Vishnu Raj, Gouthaman KV, Shiv Gehlot +2
We present GMLv2, a reference-based model designed for the prediction of subjective audio quality as measured by MUSHRA scores. GMLv2 introduces a Beta distribution-based loss to m…
eess.AS2025
Towards Evaluating Generative Audio: Insights from Neural Audio Codec Embedding Distances
Arijit Biswas, Lars Villemoes
Neural audio codecs (NACs) achieve low-bitrate compression by learning compact audio representations, which can also serve as features for perceptual quality evaluation. We introdu…