11 papers
Towards Neural Audio Codec Source Parsing
Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar +2
A new class of audio deepfakes-codecfakes (CFs)-has recently caught attention, synthesized by Audio Language Models that leverage neural audio codecs (NACs) in the backend. In resp…
HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition
Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar +4
Compression-based representations (CBRs) from neural audio codecs such as EnCodec capture intricate acoustic features like pitch and timbre, while representation-learning-based rep…
SNIFR : Boosting Fine-Grained Child Harmful Content Detection Through Audio-Visual Alignment with Cascaded Cross-Transformer
Orchid Chetia Phukan, Mohd Mujtaba Akhtar, Girish +8
As video-sharing platforms have grown over the past decade, child viewership has surged, increasing the need for precise detection of harmful content like violence or explicit scen…
Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models
Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar +5
In this work, we introduce the task of singing voice deepfake source attribution (SVDSA). We hypothesize that multimodal foundation models (MMFMs) such as ImageBind, LanguageBind w…
Are Mamba-based Audio Foundation Models the Best Fit for Non-Verbal Emotion Recognition?
Mohd Mujtaba Akhtar, Orchid Chetia Phukan, Girish +5
In this work, we focus on non-verbal vocal sounds emotion recognition (NVER). We investigate mamba-based audio foundation models (MAFMs) for the first time for NVER and hypothesize…
Investigating the Reasonable Effectiveness of Speaker Pre-Trained Models and their Synergistic Power for SingMOS Prediction
Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar +4
In this study, we focus on Singing Voice Mean Opinion Score (SingMOS) prediction. Previous research have shown the performance benefit with the use of state-of-the-art (SOTA) pre-t…