Picture for Sameer Khurana

Sameer Khurana

SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers

Add code
Apr 02, 2024
Viaarxiv icon

NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization

Add code
Feb 27, 2024
Viaarxiv icon

NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection

Add code
Dec 12, 2023
Viaarxiv icon

Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction

Add code
Oct 30, 2023
Viaarxiv icon

Generation or Replication: Auscultating Audio Latent Diffusion Models

Add code
Oct 16, 2023
Viaarxiv icon

Direct Text to Speech Translation System using Acoustic Units

Add code
Sep 14, 2023
Viaarxiv icon

Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers

Add code
Jul 06, 2023
Viaarxiv icon

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Add code
Jun 01, 2023
Viaarxiv icon

Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages

Add code
May 21, 2023
Viaarxiv icon

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

Add code
Nov 14, 2022
Viaarxiv icon