WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
hub
Megatts 3: Sparse alignment enhanced latent diffusion transformer for zero-shot 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
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
CoSyncDiT is a cognitive-inspired diffusion transformer that achieves state-of-the-art lip synchronization and naturalness in movie dubbing by guiding noise-to-speech generation through acoustic, visual, and contextual stages plus joint regularization.
Voice conversion in interactive studies boosts user trust in SpeechLLM responses while automated metrics detect accent-by-gender disparities in alignment and verbosity.
ScenA generates multi-speaker audio scenes by conditioning a flow-matching foundation model on reference voices and natural language prompts, using a high-noise-biased timestep schedule to prevent reference shortcut.
ASR self-verification via best-of-N sampling eliminates observed catastrophic failures in multiple neural-codec TTS models, with distillation transferring most of the robustness to single-shot decoding.
EmoInstruct-TTS uses Emotion2embed and an Instruction-Conditioned Emotion Flow Model (ICE-Flow) to generate acoustically grounded emotion representations from free-form instructions and integrate them into an LLM-based TTS pipeline.
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.
By training flow-matching TTS to avoid augmented repeat/skip latent trajectories, RobustSpeechFlow cuts Seed-TTS-eval WER from 1.44 to 1.38 and improves CER on a new multilingual benchmark.
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.
JAM-Flow introduces a unified flow-matching model with a Multi-Modal Diffusion Transformer that jointly synthesizes facial motion and speech from text, audio, or motion inputs.
Introduces joint residual reweighting that disentangles speaker and joint residuals in CFG to improve speaker fidelity while preserving text accuracy in zero-shot TTS.
VoxCPM2 scales hierarchical continuous-latent speech modeling to 2B parameters and over 2M hours of multilingual data, unifying voice cloning, style control, and continuation in one backbone with open release.
MLLM-enabled video translation is usefully framed as three roles—Semantic Reasoner, Expressive Performer, and Visual Synthesizer—rather than a cascade of ASR, MT, TTS, and lip-sync.
LLMs persuade effectively in human debates yet fail to comprehend deeper dialogical structures such as argument quality and supporting premises.
citing papers explorer
-
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
-
CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing
CoSyncDiT is a cognitive-inspired diffusion transformer that achieves state-of-the-art lip synchronization and naturalness in movie dubbing by guiding noise-to-speech generation through acoustic, visual, and contextual stages plus joint regularization.
-
From Seeing it to Experiencing it: Interactive Evaluation of Intersectional Voice Bias in Human-AI Speech Interaction
Voice conversion in interactive studies boosts user trust in SpeechLLM responses while automated metrics detect accent-by-gender disparities in alignment and verbosity.
-
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
ScenA generates multi-speaker audio scenes by conditioning a flow-matching foundation model on reference voices and natural language prompts, using a high-noise-biased timestep schedule to prevent reference shortcut.
-
Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs
ASR self-verification via best-of-N sampling eliminates observed catastrophic failures in multiple neural-codec TTS models, with distillation transferring most of the robustness to single-shot decoding.
-
EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis
EmoInstruct-TTS uses Emotion2embed and an Instruction-Conditioned Emotion Flow Model (ICE-Flow) to generate acoustically grounded emotion representations from free-form instructions and integrate them into an LLM-based TTS pipeline.
-
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.
-
RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
By training flow-matching TTS to avoid augmented repeat/skip latent trajectories, RobustSpeechFlow cuts Seed-TTS-eval WER from 1.44 to 1.38 and improves CER on a new multilingual benchmark.
-
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.
-
JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching
JAM-Flow introduces a unified flow-matching model with a Multi-Modal Diffusion Transformer that jointly synthesizes facial motion and speech from text, audio, or motion inputs.
-
Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
Introduces joint residual reweighting that disentangles speaker and joint residuals in CFG to improve speaker fidelity while preserving text accuracy in zero-shot TTS.
-
VoxCPM2 Technical Report
VoxCPM2 scales hierarchical continuous-latent speech modeling to 2B parameters and over 2M hours of multilingual data, unifying voice cloning, style control, and continuation in one backbone with open release.
-
Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
MLLM-enabled video translation is usefully framed as three roles—Semantic Reasoner, Expressive Performer, and Visual Synthesizer—rather than a cascade of ASR, MT, TTS, and lip-sync.
-
The Thin Line Between Comprehension and Persuasion in LLMs
LLMs persuade effectively in human debates yet fail to comprehend deeper dialogical structures such as argument quality and supporting premises.
- dots.tts Technical Report