Hello! I'm a final year MS student at IIIT Hyderabad, researching on multi-modal deep learning applications, involving computer vision, speech synthesis, ...
IIIT Hyderabad - Cited by 3 - Multimodal AI - Speech Synthesis - Text-to-Speech - Generative AI
Jul 3, 2023 · RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations. Authors:Neha Sahipjohn, Neil Shah, Vishal ...
Neha Sahipjohn's 6 research works with 4 citations, including: StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin.
Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces.
ParrotTTS: Text-to-speech synthesis exploiting disentangled self-supervised representations. By Neil Shah, Saiteja Kosgi, Vishal Tambrahalli, Neha Sahipjohn, ...
Publication Topics. Mean Opinion Score,Adversarial Attacks,Adversarial Robustness,Attack Success,Attack Success Rate,Authentication System,Background Noise ...
Neha Sahipjohn. orcid logo. 0009-0009-1101-8701. content_copy print. expand_less Show record summary. No ...
Oct 4, 2024 · View information about presenter's schedule and topics within the conference supported by SIGCHI and ACM.