13 citations · 19 across the 14 of their papers we have counts for
7 papers · 1 filter
Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Sounds
JaeHyeong Chang, Chengzhe Sun, Siwei Lyu
We investigate whether AI-generated impulsive sounds can be distinguished from real ones through group delay analysis. Our central finding is that AI-generated impulsive sounds sho…
Directional Contextual Representations for Dependency Relations: Why Cross-Direction Pairing Fails
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1
Splitting a bidirectional LSTM's contextual representation into a forward-only (strictly a function of tokens ) and a backward-only (strictly a function of tokens…
Sparse Token Routing in Efficient Transformers
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1
Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational effort. We test this claim end…
The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints
Tianle Yang, Cuiling Zhang, Chengzhe Sun +2
In recent years, the term voiceprint has regained attention, particularly in technological applications and policy-making contexts, often carrying the assumption that a person's vo…
A survey of AI-generated voices and their detection
Chengzhe Sun, Tianle Yang, Siwei Lyu
The ability of artificial intelligence (AI) models to generate highly realistic human voices has advanced rapidly. These technologies power accessibility tools, virtual assistants…
Acoustic and perceptual differences between standard and accented speech and their voice clones
Tianle Yang, Chengzhe Sun, Phil Rose +1
Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences. We compare standard and heavily accented…
Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation
Tianle Yang, Chengzhe Sun, Phil Rose +2
This study proposes a segmental-level prosodic probing framework to evaluate neural TTS models' ability to reproduce consonant-induced f0 perturbation, a fine-grained segmental-pro…