Cover Image

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Karita, Shigeki, Koizumi, Yuma, Zen, Heiga, Ishikawa, Haruko, Scheibler, Robin, Bacchiani, Michiel
Format:	Preprint
Published:	2025
Subjects:	Sound Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability
by: Nakata, Wataru, et al.
Published: (2025)

FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks
by: Ma, Min, et al.
Published: (2024)

Universal Score-based Speech Enhancement with High Content Preservation
by: Scheibler, Robin, et al.
Published: (2024)

Translatotron 3: Speech to Speech Translation with Monolingual Data
by: Nachmani, Eliya, et al.
Published: (2023)

SimulTron: On-Device Simultaneous Speech to Speech Translation
by: Agranovich, Alex, et al.
Published: (2024)

VoiceRestore: Flow-Matching Transformers for Speech Recording Quality Restoration
by: Kirdey, Stanislav
Published: (2025)

Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data
by: Saeki, Takaaki, et al.
Published: (2024)

Less is More: Data Curation Matters in Scaling Speech Enhancement
by: Li, Chenda, et al.
Published: (2025)

URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement
by: Zhang, Wangyou, et al.
Published: (2024)

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
by: Ku, Pin-Jui, et al.
Published: (2024)

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

VC-ENHANCE: Speech Restoration with Integrated Noise Suppression and Voice Conversion
by: Byun, Kyungguen, et al.
Published: (2024)

FLOWER: Flow-Based Estimated Gaussian Guidance for General Speech Restoration
by: Yang, Da-Hee, et al.
Published: (2025)

Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning
by: Ohnaka, Hien, et al.
Published: (2025)

Source Separation by Flow Matching
by: Scheibler, Robin, et al.
Published: (2025)

Restorative Speech Enhancement: A Progressive Approach Using SE and Codec Modules
by: Chiang, Hsin-Tien, et al.
Published: (2024)

Listen through the Sound: Generative Speech Restoration Leveraging Acoustic Context Representation
by: Chung, Soo-Whan, et al.
Published: (2025)

From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition
by: Wang, Tianduo, et al.
Published: (2025)

Voice-ENHANCE: Speech Restoration using a Diffusion-based Voice Conversion Framework
by: Byun, Kyungguen, et al.
Published: (2025)

Scaling Speech-Text Pre-training with Synthetic Interleaved Data
by: Zeng, Aohan, et al.
Published: (2024)

SEMamba++: A General Speech Restoration Framework Leveraging Global, Local, and Periodic Spectral Patterns
by: Lee, Yongjoon, et al.
Published: (2026)

Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing
by: Nakata, Wataru, et al.
Published: (2025)

Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition
by: Vesterbacka, Leonora, et al.
Published: (2025)

SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation
by: Zhang, Dong, et al.
Published: (2024)

Inappropriate Pause Detection In Dysarthric Speech Using Large-Scale Speech Recognition
by: Lee, Jeehyun, et al.
Published: (2024)

Simultaneous Speech-to-Speech Translation Without Aligned Data
by: Labiausse, Tom, et al.
Published: (2026)

Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
by: Parcollet, Titouan, et al.
Published: (2025)

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning
by: Peng, Yifan, et al.
Published: (2025)

Adaptive Dropout for Pruning Conformers
by: Kubo, Yotaro, et al.
Published: (2024)

Scaling Analysis of Interleaved Speech-Text Language Models
by: Maimon, Gallil, et al.
Published: (2025)

CASPER: A Large Scale Spontaneous Speech Dataset
by: Xiao, Cihan, et al.
Published: (2025)

A Diffusion-Based Generative Equalizer for Music Restoration
by: Moliner, Eloi, et al.
Published: (2024)

USAD: Universal Speech and Audio Representation via Distillation
by: Chang, Heng-Jui, et al.
Published: (2025)

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark
by: Shi, Jiatong, et al.
Published: (2023)

URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement Competition
by: Wang, Jiahe, et al.
Published: (2025)

Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
by: Cornell, Samuele, et al.
Published: (2024)

Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection
by: Lin, Hsi-Che, et al.
Published: (2024)

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs
by: Ma, Rao, et al.
Published: (2025)

Wave-Trainer-Fit: Neural Vocoder with Trainable Prior and Fixed-Point Iteration towards High-Quality Speech Generation from SSL features
by: Ohnaka, Hien, et al.
Published: (2026)

Dynamic Data Pruning for Automatic Speech Recognition
by: Xiao, Qiao, et al.
Published: (2024)