FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates like 6.25 Hz.
Semantic Distill
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.SD 3years
2026 3verdicts
UNVERDICTED 3representative 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
-
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates like 6.25 Hz.
-
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.