Introduces the Indic-CodecFake dataset for Indic codec deepfakes and SATYAM, a novel hyperbolic ALM that outperforms baselines through dual-stage semantic-prosodic fusion using Bhattacharya distance.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
VALL-E is a neural codec language model trained on 60K hours of speech that performs zero-shot TTS, synthesizing natural speech that matches an unseen speaker's voice, emotion, and environment from a 3-second prompt.
APC embeds compact Ed25519 signatures into audio phase data with error correction to achieve 97.5-98.3% cryptographic verification under eight attack types at mean PESQ 3.02.
RuASD is a comprehensive Russian speech anti-spoofing dataset featuring 37 synthesis systems and a robustness evaluation pipeline for real-world channel distortions.
A system based on OmniVoice with multi-model ensemble distillation for fine-tuning shows consistent gains in intelligibility metrics while keeping speaker similarity for cross-lingual scientific speech.
XR-CareerAssist fuses XR and five AI modules into a Unity-based immersive platform for multilingual, personalized career guidance via 3D avatars and dynamic Sankey diagrams, reporting 78.3% user satisfaction in a 23-person pilot.
Voice range indicates TTS model capability with VITS highest, Glow-TTS best at soft phonation, and CPPs of 7-8 dB marking natural quality while values over 10 dB sound robotic.
citing papers explorer
-
Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages
Introduces the Indic-CodecFake dataset for Indic codec deepfakes and SATYAM, a novel hyperbolic ALM that outperforms baselines through dual-stage semantic-prosodic fusion using Bhattacharya distance.
-
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
VALL-E is a neural codec language model trained on 60K hours of speech that performs zero-shot TTS, synthesizing natural speech that matches an unseen speaker's voice, emotion, and environment from a 3-second prompt.
-
Asymmetric Phase Coding Audio Watermarking
APC embeds compact Ed25519 signatures into audio phase data with error correction to achieve 97.5-98.3% cryptographic verification under eight attack types at mean PESQ 3.02.
-
Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative
RuASD is a comprehensive Russian speech anti-spoofing dataset featuring 37 synthesis systems and a robustness evaluation pipeline for real-world channel distortions.
-
One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech
A system based on OmniVoice with multi-model ensemble distillation for fine-tuning shows consistent gains in intelligibility metrics while keeping speaker similarity for cross-lingual scientific speech.
-
XR-CareerAssist: An Immersive Platform for Personalised Career Guidance Leveraging Extended Reality and Multimodal AI
XR-CareerAssist fuses XR and five AI modules into a Unity-based immersive platform for multilingual, personalized career guidance via 3D avatars and dynamic Sankey diagrams, reporting 78.3% user satisfaction in a 23-person pilot.
-
Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment
Voice range indicates TTS model capability with VITS highest, Glow-TTS best at soft phonation, and CPPs of 7-8 dB marking natural quality while values over 10 dB sound robotic.