The paper introduces a subjective-objective evaluation framework using Best Worst Scaling and a novel dual-reference distributional measure to better assess intelligibility versus speaker identity trade-offs in TTS voice reconstruction.
Semantic Distill
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
MimicLM achieves better naturalness in zero-shot voice imitation by autoregressively modeling pseudo-parallel data with synthetic sources and real targets, plus interleaved text-audio guidance and preference alignment.
A singing voice conversion system with boundary-aware information bottleneck and high-frequency augmentation achieves the best naturalness in SVCC2025 subjective tests while using less extra data than competitors.
citing papers explorer
-
An Evaluation Framework for Text-to-Speech Voice Reconstruction
The paper introduces a subjective-objective evaluation framework using Best Worst Scaling and a novel dual-reference distributional measure to better assess intelligibility versus speaker identity trade-offs in TTS voice reconstruction.
-
MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora
MimicLM achieves better naturalness in zero-shot voice imitation by autoregressively modeling pseudo-parallel data with synthetic sources and real targets, plus interleaved text-audio guidance and preference alignment.
-
Controllable Singing Style Conversion with Boundary-Aware Information Bottleneck
A singing voice conversion system with boundary-aware information bottleneck and high-frequency augmentation achieves the best naturalness in SVCC2025 subjective tests while using less extra data than competitors.
- FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates