Picture for Rita Singh

Rita Singh

A New Benchmark for Few-Shot Class-Incremental Learning: Redefining the Upper Bound

Add code
Mar 13, 2025
Viaarxiv icon

Mellow: a small audio language model for reasoning

Add code
Mar 11, 2025
Viaarxiv icon

On the Robust Approximation of ASR Metrics

Add code
Feb 18, 2025
Viaarxiv icon

Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models

Add code
Feb 18, 2025
Viaarxiv icon

ADIFF: Explaining audio difference using natural language

Add code
Feb 06, 2025
Viaarxiv icon

Tessellated Linear Model for Age Prediction from Voice

Add code
Jan 16, 2025
Figure 1 for Tessellated Linear Model for Age Prediction from Voice
Figure 2 for Tessellated Linear Model for Age Prediction from Voice
Figure 3 for Tessellated Linear Model for Age Prediction from Voice
Figure 4 for Tessellated Linear Model for Age Prediction from Voice
Viaarxiv icon

What Do Speech Foundation Models Not Learn About Speech?

Add code
Oct 16, 2024
Figure 1 for What Do Speech Foundation Models Not Learn About Speech?
Figure 2 for What Do Speech Foundation Models Not Learn About Speech?
Figure 3 for What Do Speech Foundation Models Not Learn About Speech?
Figure 4 for What Do Speech Foundation Models Not Learn About Speech?
Viaarxiv icon

Objective Measurements of Voice Quality

Add code
Oct 12, 2024
Figure 1 for Objective Measurements of Voice Quality
Figure 2 for Objective Measurements of Voice Quality
Figure 3 for Objective Measurements of Voice Quality
Viaarxiv icon

Improving Speaker Representations Using Contrastive Losses on Multi-scale Features

Add code
Oct 07, 2024
Viaarxiv icon

Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection

Add code
Oct 04, 2024
Viaarxiv icon