Publications (9)
Learning Perceptually Relevant Temporal Envelope Morphing
Satvik Dixit, Sungjoon Park, Chris Donahue +1
Temporal envelope morphing, the process of interpolating between the amplitude dynamics of two audio signals, is an emerging problem in generative audio systems that lacks sufficie…
MACE: Leveraging Audio for Evaluating Audio Captioning Systems
Satvik Dixit, Soham Deshmukh, Bhiksha Raj
The Automated Audio Captioning (AAC) task aims to describe an audio signal using natural language. To evaluate machine-generated captions, the metrics should take into account audi…
Explaining Deep Learning Embeddings for Speech Emotion Recognition by Predicting Interpretable Acoustic Features
Satvik Dixit, Daniel M. Low, Gasser Elbanna +2
Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic f…
AURA Score: A Metric For Holistic Audio Question Answering Evaluation
Satvik Dixit, Soham Deshmukh, Bhiksha Raj
Audio Question Answering (AQA) is a key task for evaluating Audio-Language Models (ALMs), yet assessing open-ended responses remains challenging. Existing metrics used for AQA such…
MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence
Sonal Kumar, Å imon SedláÄek, Vaibhavi Lokegaonkar +31
Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio unde…
Improving Speaker Representations Using Contrastive Losses on Multi-scale Features
Satvik Dixit, Massa Baali, Rita Singh +1
Speaker verification systems have seen significant advancements with the introduction of Multi-scale Feature Aggregation (MFA) architectures, such as MFA-Conformer and ECAPA-TDNN.…
Mellow: a small audio language model for reasoning
Soham Deshmukh, Satvik Dixit, Rita Singh +1
Multimodal Audio-Language Models (ALMs) can understand and reason over both audio and text. Typically, reasoning performance correlates with model size, with the best results achie…
Vision Language Models Are Few-Shot Audio Spectrogram Classifiers
Satvik Dixit, Laurie M. Heller, Chris Donahue
We demonstrate that vision language models (VLMs) are capable of recognizing the content in audio recordings when given corresponding spectrogram images. Specifically, we instruct…
FoleyBench: A Benchmark For Video-to-Audio Models
Satvik Dixit, Koichi Saito, Zhi Zhong +2
Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects s…