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.
hub
Fish-speech: Lever- aging large language models for advanced multilingual text-to- speech synthesis
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
representative citing papers
Poly-SVC converts singing voices from polyphonic recordings while keeping melody, lyrics, and harmonies by combining CQT-based pitch extraction with a conditional flow matching diffusion decoder.
V.O.I.C.E is a new taxonomy that organizes synthetic voice risks into five categories and shows how they interact with exposure, visibility, and legal context using empirical incident data.
NVBench provides a standardized bilingual benchmark and evaluation protocol for assessing non-verbal vocalization generation, placement, and salience in text-to-speech systems.
EchoFake is a new replay-aware dataset combining zero-shot TTS deepfakes and physical replay recordings to improve generalization of speech deepfake detection models over existing lab-focused datasets.
MindVoice disentangles neural-to-speech reconstruction into semantic and acoustic pathways using pretrained priors, then fuses them with speech generation models to produce intelligible output from non-invasive recordings.
SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.
RTCFake is the first large-scale dataset of real-time communication speech deepfakes paired with offline versions, paired with a phoneme-guided consistency learning method that improves cross-platform and noise-robust detection.
OmniVoice introduces a diffusion language model-style non-autoregressive TTS system that directly maps text to multi-codebook acoustic tokens, scaling zero-shot synthesis to over 600 languages with SOTA results on multilingual benchmarks using 581k hours of open data.
RuASD is a comprehensive Russian speech anti-spoofing dataset featuring 37 synthesis systems and a robustness evaluation pipeline for real-world channel distortions.
Qwen3-TTS delivers state-of-the-art multilingual TTS performance with 3-second voice cloning, description control, and ultra-low-latency streaming via dual tokenizers and a dual-track LM architecture trained on over 5 million hours of data.
A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.
Omni-Fake delivers a unified multimodal deepfake benchmark dataset and RL-driven detector that reports gains in accuracy, cross-modal generalization, and explainability over prior baselines.
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.
-
Poly-SVC: Polyphony-Aware Singing Voice Conversion with Harmonic Modeling
Poly-SVC converts singing voices from polyphonic recordings while keeping melody, lyrics, and harmonies by combining CQT-based pitch extraction with a conditional flow matching diffusion decoder.
-
V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data
V.O.I.C.E is a new taxonomy that organizes synthetic voice risks into five categories and shows how they interact with exposure, visibility, and legal context using empirical incident data.
-
NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations
NVBench provides a standardized bilingual benchmark and evaluation protocol for assessing non-verbal vocalization generation, placement, and salience in text-to-speech systems.
-
EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection
EchoFake is a new replay-aware dataset combining zero-shot TTS deepfakes and physical replay recordings to improve generalization of speech deepfake detection models over existing lab-focused datasets.
-
MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors
MindVoice disentangles neural-to-speech reconstruction into semantic and acoustic pathways using pretrained priors, then fuses them with speech generation models to produce intelligible output from non-invasive recordings.
-
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.
-
RTCFake: Speech Deepfake Detection in Real-Time Communication
RTCFake is the first large-scale dataset of real-time communication speech deepfakes paired with offline versions, paired with a phoneme-guided consistency learning method that improves cross-platform and noise-robust detection.
-
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
OmniVoice introduces a diffusion language model-style non-autoregressive TTS system that directly maps text to multi-codebook acoustic tokens, scaling zero-shot synthesis to over 600 languages with SOTA results on multilingual benchmarks using 581k hours of open data.
-
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.
-
Qwen3-TTS Technical Report
Qwen3-TTS delivers state-of-the-art multilingual TTS performance with 3-second voice cloning, description control, and ultra-low-latency streaming via dual tokenizers and a dual-track LM architecture trained on over 5 million hours of data.
-
Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.
-
Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
Omni-Fake delivers a unified multimodal deepfake benchmark dataset and RL-driven detector that reports gains in accuracy, cross-modal generalization, and explainability over prior baselines.
- Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
- When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus