Buchumschlag

Selecting N-lowest scores for training MOS prediction models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kondo, Yuto, Kameoka, Hirokazu, Tanaka, Kou, Kaneko, Takuhiro
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Sound Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models
von: Kameoka, Hirokazu, et al.
Veröffentlicht: (2025)

Rethinking Mean Opinion Scores in Speech Quality Assessment: Aggregation through Quantized Distribution Fitting
von: Kondo, Yuto, et al.
Veröffentlicht: (2025)

JIS: A Speech Corpus of Japanese Idol Speakers with Various Speaking Styles
von: Kondo, Yuto, et al.
Veröffentlicht: (2025)

Vocoder-Projected Feature Discriminator
von: Kaneko, Takuhiro, et al.
Veröffentlicht: (2025)

FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
von: Kaneko, Takuhiro, et al.
Veröffentlicht: (2025)

MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flows
von: Kaneko, Takuhiro, et al.
Veröffentlicht: (2026)

FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation
von: Kaneko, Takuhiro, et al.
Veröffentlicht: (2024)

Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
von: Kaneko, Takuhiro, et al.
Veröffentlicht: (2024)

VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
von: Kameoka, Hirokazu, et al.
Veröffentlicht: (2020)

GE2E-AC: Generalized End-to-End Loss Training for Accent Classification
von: Watanabe, Chihiro, et al.
Veröffentlicht: (2024)

SingMOS: An extensive Open-Source Singing Voice Dataset for MOS Prediction
von: Tang, Yuxun, et al.
Veröffentlicht: (2024)

The AudioMOS Challenge 2025
von: Huang, Wen-Chin, et al.
Veröffentlicht: (2025)

CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents
von: Huang, Wen-Chin, et al.
Veröffentlicht: (2026)

The VoiceMOS Challenge 2024: Beyond Speech Quality Prediction
von: Huang, Wen-Chin, et al.
Veröffentlicht: (2024)

ASTAR-NTU solution to AudioMOS Challenge 2025 Track1
von: Ritter-Gutierrez, Fabian, et al.
Veröffentlicht: (2025)

MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models
von: Huang, Wen-Chin, et al.
Veröffentlicht: (2024)

SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features
von: Shi, Yu-Fei, et al.
Veröffentlicht: (2024)

Analysing the Masked predictive coding training criterion for pre-training a Speech Representation Model
von: Yadav, Hemant, et al.
Veröffentlicht: (2023)

Investigating the Reasonable Effectiveness of Speaker Pre-Trained Models and their Synergistic Power for SingMOS Prediction
von: Phukan, Orchid Chetia, et al.
Veröffentlicht: (2025)

APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech
von: Lian, Zhicheng, et al.
Veröffentlicht: (2025)

Quality Assessment of Noisy and Enhanced Speech with Limited Data: UWB-NTIS System for VoiceMOS 2024
von: Kunešová, Marie, et al.
Veröffentlicht: (2025)

Learning to assess subjective impressions from speech
von: Kondo, Yuto, et al.
Veröffentlicht: (2025)

Multi-Sampling-Frequency Naturalness MOS Prediction Using Self-Supervised Learning Model with Sampling-Frequency-Independent Layer
von: Nishikawa, Go, et al.
Veröffentlicht: (2025)

The T12 System for AudioMOS Challenge 2025: Audio Aesthetics Score Prediction System Using KAN- and VERSA-based Models
von: Yamamoto, Katsuhiko, et al.
Veröffentlicht: (2025)

A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models
von: Whetten, Ryan, et al.
Veröffentlicht: (2026)

Bridging the gap between training and inference in LM-based TTS models
von: Zhang, Ruonan, et al.
Veröffentlicht: (2025)

Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline
von: Riley, Xavier, et al.
Veröffentlicht: (2024)

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

SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment
von: Tang, Yuxun, et al.
Veröffentlicht: (2025)

Real-time Speech Extraction Using Spatially Regularized Independent Low-rank Matrix Analysis and Rank-constrained Spatial Covariance Matrix Estimation
von: Ishikawa, Yuto, et al.
Veröffentlicht: (2024)

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
von: Nishimura, Yuto, et al.
Veröffentlicht: (2024)

Misophonia Trigger Sound Detection on Synthetic Soundscapes Using a Hybrid Model with a Frozen Pre-Trained CNN and a Time-Series Module
von: Sashida, Kurumi, et al.
Veröffentlicht: (2026)

An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech
von: Deng, Qingkun, et al.
Veröffentlicht: (2024)

WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction
von: Emon, Jakaria Islam, et al.
Veröffentlicht: (2025)

The TMU System for the XACLE Challenge: Training Large Audio Language Models with CLAP Pseudo-Labels
von: Tsutsumi, Ayuto, et al.
Veröffentlicht: (2026)

Consistency Based Unsupervised Self-training For ASR Personalisation
von: Zhang, Jisi, et al.
Veröffentlicht: (2024)

Event Classification by Physics-informed Inpainting for Distributed Multichannel Acoustic Sensor with Partially Degraded Channels
von: Tonami, Noriyuki, et al.
Veröffentlicht: (2026)

Trainingless Adaptation of Pretrained Models for Environmental Sound Classification
von: Tonami, Noriyuki, et al.
Veröffentlicht: (2024)

LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations
von: Dutta, Soumya, et al.
Veröffentlicht: (2025)

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
von: Zhu, Xiaoxu, et al.
Veröffentlicht: (2025)