REVIEW 27 cited by
MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
While recent zero-shot text-to-speech (TTS) models have significantly improved speech quality and expressiveness, mainstream systems still suffer from issues related to speech-text alignment modeling: 1) models without explicit speech-text alignment modeling exhibit less robustness, especially for hard sentences in practical applications; 2) predefined alignment-based models suffer from naturalness constraints of forced alignments. This paper introduces \textit{MegaTTS 3}, a TTS system featuring an innovative sparse alignment algorithm that guides the latent diffusion transformer (DiT). Specifically, we provide sparse alignment boundaries to MegaTTS 3 to reduce the difficulty of alignment without limiting the search space, thereby achieving high naturalness. Moreover, we employ a multi-condition classifier-free guidance strategy for accent intensity adjustment and adopt the piecewise rectified flow technique to accelerate the generation process. Experiments demonstrate that MegaTTS 3 achieves state-of-the-art zero-shot TTS speech quality and supports highly flexible control over accent intensity. Notably, our system can generate high-quality one-minute speech with only 8 sampling steps. Audio samples are available at https://sditdemo.github.io/sditdemo/.
Forward citations
Cited by 27 Pith papers
-
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 contextua...
-
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.
-
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
Hierarchical multi-prompt representation generation plus generalized flow matching yields high-quality single-stage waveform diffusion from 12.5 Hz latents and efficient LDM TTS.
-
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
SwanTale unifies instruction-driven and zero-shot speech and audio generation in one 48 kHz model, with a large captioning pipeline, and reports leading scores on several expressiveness and instruction-following benchmarks.
-
DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
Block discrete diffusion over X-Codec2 tokens yields competitive zero-shot TTS with 0.6B parameters, 20K training hours, and a 0.15 real-time factor.
-
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-base...
-
dots.tts Technical Report
dots.tts reports SOTA benchmark results on Seed-TTS-Eval and other tests via continuous latent-space autoregressive modeling with three listed innovations and code release.
-
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.
-
RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
RobustSpeechFlow improves TTS alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations, lowering WER from 1.44 to 1.38 on Seed-TTS-eval and CER on ZERO500.
-
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 mul...
-
UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
A single LLM can do ASR and zero-shot TTS on continuous speech features by switching between causal and bidirectional attention, reaching competitive but not state-of-the-art results.
-
DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration
DiTReducio is a training-free, pattern-guided layer and branch skipping method that accelerates DiT-based TTS, reporting significant FLOP and RTF reductions with modest quality loss at tuned thresholds.
-
Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
A cross-attention term retriever estimates which terminology appears in speech and, when its top-k terms are added to the prompt, improves SLM terminology accuracy by 6-17%.
-
JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
JAM is a 530M-parameter flow-matching song generator that adds word- and phoneme-level timing control and duration control, achieving strong lyric fidelity and musicality scores when ground-truth timings are provided.
-
Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
A new attack framework, TrojanClimb, shows that adversaries can place models with embedded backdoors or biases on public leaderboards while retaining competitive rankings, across text embeddings, text generation, spee...
-
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 decomposes CFG guidance into text, speaker, and joint residuals and reweights the joint term independently to improve speaker similarity while preserving text correctness in ...
-
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.
-
DETECT-3B-Omni is Agnostic of Content and Demographics
Equivalence tests on 10,240 samples find DETECT-3B-Omni accuracy differs by ≤2pp across content type and speaker demographics at 99% confidence.
-
Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.
Discussion (0). Sign in to comment.