Cover Image

MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	An, Keyu, Zhang, Zhiyu, Gao, Changfeng, Li, Yabin, Peng, Zhendong, Wang, Haoxu, Du, Zhihao, Zhao, Han, Gao, Zhifu, Li, Xiangang
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Explore the Reinforcement Learning for the LLM based ASR and TTS system
by: Gao, Changfeng, et al.
Published: (2025)

Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition
by: An, Keyu, et al.
Published: (2024)

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS
by: Wang, Cong, et al.
Published: (2025)

Differentiable Reward Optimization for LLM based TTS system
by: Gao, Changfeng, et al.
Published: (2025)

Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap
by: Yang, Guanrou, et al.
Published: (2024)

TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with ControlNet
by: Jeong, Jaeseok, et al.
Published: (2025)

CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment
by: Liu, Hanwen, et al.
Published: (2026)

I2TTS: Image-indicated Immersive Text-to-speech Synthesis with Spatial Perception
by: Zhang, Jiawei, et al.
Published: (2024)

DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation
by: Wang, Jianzong, et al.
Published: (2023)

FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning
by: Wang, Haoxu, et al.
Published: (2026)

E2E-AEC: Implementing an end-to-end neural network learning approach for acoustic echo cancellation
by: Jiang, Yiheng, et al.
Published: (2026)

Joint decoding method for controllable contextual speech recognition based on Speech LLM
by: Fang, Yangui, et al.
Published: (2025)

Exploring speech style spaces with language models: Emotional TTS without emotion labels
by: Chandra, Shreeram Suresh, et al.
Published: (2024)

CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
by: Du, Zhihao, et al.
Published: (2025)

Prosodic Parameter Manipulation in TTS generated speech for Controlled Speech Generation
by: Chary, Podakanti Satyajith
Published: (2024)

Expressive paragraph text-to-speech synthesis with multi-step variational autoencoder
by: Li, Xuyuan, et al.
Published: (2023)

StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis
by: Chen, Zhiyong, et al.
Published: (2024)

CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
by: Du, Zhihao, et al.
Published: (2024)

Fun-ASR Technical Report
by: An, Keyu, et al.
Published: (2025)

TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch
by: Song, Xingchen, et al.
Published: (2024)

Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech
by: Li, Zirui, et al.
Published: (2025)

SponTTS: modeling and transferring spontaneous style for TTS
by: Li, Hanzhao, et al.
Published: (2023)

E1 TTS: Simple and Fast Non-Autoregressive TTS
by: Liu, Zhijun, et al.
Published: (2024)

ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement
by: Wang, Haoxu, et al.
Published: (2025)

Scalable Controllable Accented TTS
by: Xinyuan, Henry Li, et al.
Published: (2025)

Traceable TTS: Toward Watermark-Free TTS with Strong Traceability
by: Zhao, Yuxiang, et al.
Published: (2025)

Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion
by: Ai, Jiabao, et al.
Published: (2026)

AlignNet: Learning dataset score alignment functions to enable better training of speech quality estimators
by: Pieper, Jaden, et al.
Published: (2024)

Using RLHF to align speech enhancement approaches to mean-opinion quality scores
by: Kumar, Anurag, et al.
Published: (2024)

Efficient training strategies for natural sounding speech synthesis and speaker adaptation based on FastPitch
by: Răgman, Teodora, et al.
Published: (2024)

Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks
by: Maiti, Soumi, et al.
Published: (2023)

Exploring synthetic data for cross-speaker style transfer in style representation based TTS
by: Ueda, Lucas H., et al.
Published: (2024)

End-to-end multi-channel speaker extraction and binaural speech synthesis
by: Chi, Cheng, et al.
Published: (2024)

VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation
by: Peng, Puyuan, et al.
Published: (2025)

How Open is Open TTS? A Practical Evaluation of Open Source TTS Tools
by: Răgman, Teodora, et al.
Published: (2026)

Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS
by: Li, Haoyu, et al.
Published: (2025)

Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
by: Fujita, Kenichi, et al.
Published: (2024)

DAIEN-TTS: Disentangled Audio Infilling for Environment-Aware Text-to-Speech Synthesis
by: Lu, Ye-Xin, et al.
Published: (2025)

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
by: Eskimez, Sefik Emre, et al.
Published: (2024)

EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis
by: Li, Haoxun, et al.
Published: (2025)