Cover Image

Multi-Metric Preference Alignment for Generative Speech Restoration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Junan, Zhang, Xueyao, Yang, Jing, Wang, Yuancheng, Fan, Fan, Wu, Zhizheng
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Machine Learning Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
by: Wang, Yuancheng, et al.
Published: (2025)

AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement
by: Zhang, Junan, et al.
Published: (2025)

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
by: Wang, Yuancheng, et al.
Published: (2025)

MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
by: Wang, Yuancheng, et al.
Published: (2024)

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment
by: Zhang, Xueyao, et al.
Published: (2025)

VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
by: Wang, Yuxiang, et al.
Published: (2026)

Schrödinger Bridge Mamba for One-Step Speech Enhancement
by: Yang, Jing, et al.
Published: (2025)

Overview of the Amphion Toolkit (v0.2)
by: Li, Jiaqi, et al.
Published: (2025)

Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance
by: Hussain, Shehzeen, et al.
Published: (2025)

SingVERSE: A Diverse, Real-World Benchmark for Singing Voice Enhancement
by: Jiang, Shaohan, et al.
Published: (2025)

The CCF AATC 2025 Speech Restoration Challenge: A Retrospective
by: Zhang, Junan, et al.
Published: (2025)

CMGAN: Conformer-based Metric GAN for Speech Enhancement
by: Cao, Ruizhe, et al.
Published: (2022)

CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
by: Abdulatif, Sherif, et al.
Published: (2022)

LeVo: High-Quality Song Generation with Multi-Preference Alignment
by: Lei, Shun, et al.
Published: (2025)

Scaling Speech Tokenizers with Diffusion Autoencoders
by: Wang, Yuancheng, et al.
Published: (2026)

High-Resolution Speech Restoration with Latent Diffusion Model
by: Dhyani, Tushar, et al.
Published: (2024)

Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement
by: Yang, Gang, et al.
Published: (2025)

SingNet: Towards a Large-Scale, Diverse, and In-the-Wild Singing Voice Dataset
by: Gu, Yicheng, et al.
Published: (2025)

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
by: Ju, Zeqian, et al.
Published: (2024)

NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation
by: Ni, Qinke, et al.
Published: (2026)

Speech Enhancement Using Continuous Embeddings of Neural Audio Codec
by: Li, Haoyang, et al.
Published: (2025)

What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detection
by: Satish, Shree Harsha Bokkahalli, et al.
Published: (2026)

MaskSR: Masked Language Model for Full-band Speech Restoration
by: Li, Xu, et al.
Published: (2024)

Mitigating Unauthorized Speech Synthesis for Voice Protection
by: Zhang, Zhisheng, et al.
Published: (2024)

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
by: Du, Zhihao, et al.
Published: (2024)

Amphion: An Open-Source Audio, Music and Speech Generation Toolkit
by: Zhang, Xueyao, et al.
Published: (2023)

Leveraging Diverse Semantic-based Audio Pretrained Models for Singing Voice Conversion
by: Zhang, Xueyao, et al.
Published: (2023)

Music Source Restoration
by: Zang, Yongyi, et al.
Published: (2025)

KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation
by: Chung, Yoonjin, et al.
Published: (2025)

Alternating Approach-Putt Models for Multi-Stage Speech Enhancement
by: Jeong, Iksoon, et al.
Published: (2025)

Cross-Attention with Confidence Weighting for Multi-Channel Audio Alignment
by: Nihal, Ragib Amin, et al.
Published: (2025)

Single and Few-step Diffusion for Generative Speech Enhancement
by: Lay, Bunlong, et al.
Published: (2023)

Scaling Ambiguity: Augmenting Human Annotation in Speech Emotion Recognition with Audio-Language Models
by: Zhang, Wenda, et al.
Published: (2026)

VoiceBridge: General Speech Restoration with One-step Latent Bridge Models
by: Zhang, Chi, et al.
Published: (2025)

WavInWav: Time-domain Speech Hiding via Invertible Neural Network
by: Fan, Wei, et al.
Published: (2025)

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
by: Fu, Szu-Wei, et al.
Published: (2024)

Collaborative Watermarking for Adversarial Speech Synthesis
by: Juvela, Lauri, et al.
Published: (2023)

Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction
by: Mu, Zhaoxi, et al.
Published: (2023)

Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition
by: Wu, Linzhi, et al.
Published: (2026)

kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech
by: Hajal, Karl El, et al.
Published: (2024)