Image de couverture de livre

Are These Even Words? Quantifying the Gibberishness of Generative Speech Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	de Oliveira, Danilo, Peer, Tal, Rochdi, Jonas, Gerkmann, Timo
Format:	Preprint
Publié:	2025
Sujets:	Audio and Speech Processing Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models
par: Richter, Julius, et autres
Publié: (2025)

Investigating Training Objectives for Generative Speech Enhancement
par: Richter, Julius, et autres
Publié: (2024)

Do We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network Architecture
par: Richter, Julius, et autres
Publié: (2025)

Real-Time Streaming Mel Vocoding with Generative Flow Matching
par: Welker, Simon, et autres
Publié: (2025)

Too Good to Be True: A Study on Modern Automatic Speech Recognition for the Evaluation of Speech Enhancement
par: de Oliveira, Danilo, et autres
Publié: (2026)

The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement
par: de Oliveira, Danilo, et autres
Publié: (2024)

Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech
par: de Oliveira, Danilo, et autres
Publié: (2024)

An Analysis of the Variance of Diffusion-based Speech Enhancement
par: Lay, Bunlong, et autres
Publié: (2024)

Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters
par: Tesch, Kristina, et autres
Publié: (2023)

Bone-conduction Guided Multimodal Speech Enhancement with Conditional Diffusion Models
par: Khanagha, Sina, et autres
Publié: (2026)

Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
par: Makarov, Rostislav, et autres
Publié: (2025)

ReverbFX: A Dataset of Room Impulse Responses Derived from Reverb Effect Plugins for Singing Voice Dereverberation
par: Richter, Julius, et autres
Publié: (2025)

Speech Enhancement and Dereverberation with Diffusion-based Generative Models
par: Richter, Julius, et autres
Publié: (2022)

Diffusion Buffer for Online Generative Speech Enhancement
par: Lay, Bunlong, et autres
Publié: (2025)

StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
par: Lemercier, Jean-Marie, et autres
Publié: (2022)

Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios
par: Kienegger, Jakob, et autres
Publié: (2025)

Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
par: Kienegger, Jakob, et autres
Publié: (2026)

Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios
par: Kienegger, Jakob, et autres
Publié: (2026)

EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Data
par: Prabhu, Navin Raj, et autres
Publié: (2023)

Single and Few-step Diffusion for Generative Speech Enhancement
par: Lay, Bunlong, et autres
Publié: (2023)

Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation
par: Kienegger, Jakob, et autres
Publié: (2024)

Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Model
par: Lemercier, Jean-Marie, et autres
Publié: (2023)

EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
par: Richter, Julius, et autres
Publié: (2024)

The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs
par: Satish, Shree Harsha Bokkahalli, et autres
Publié: (2026)

Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance
par: Kienegger, Jakob, et autres
Publié: (2025)

Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining
par: Cheng, Ruoxi, et autres
Publié: (2024)

BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models
par: Moliner, Eloi, et autres
Publié: (2024)

Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models
par: Lemercier, Jean-Marie, et autres
Publié: (2024)

Enhancing In-the-Wild Speech Emotion Conversion with Resynthesis-based Duration Modeling
par: Prabhu, Navin Raj, et autres
Publié: (2025)

Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models
par: Jing, Ruihao, et autres
Publié: (2025)

Can LLMs Help Localize Fake Words in Partially Fake Speech?
par: Zhang, Lin, et autres
Publié: (2026)

Diffusion Models for Audio Restoration
par: Lemercier, Jean-Marie, et autres
Publié: (2024)

Integrating Pause Information with Word Embeddings in Language Models for Alzheimer's Disease Detection from Spontaneous Speech
par: Pu, Yu, et autres
Publié: (2025)

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
par: Wang, Tianrui, et autres
Publié: (2025)

Quantifying Dimensional Independence in Speech: An Information-Theoretic Framework for Disentangled Representation Learning
par: Kashyap, Bipasha, et autres
Publié: (2026)

A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restoration
par: Lay, Bunlong, et autres
Publié: (2026)

HRTF Estimation using a Score-based Prior
par: Thuillier, Etienne, et autres
Publié: (2024)

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
par: Ku, Pin-Jui, et autres
Publié: (2024)

Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation
par: Li, Jiaqi, et autres
Publié: (2024)

DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models
par: Wang, Yuanyuan, et autres
Publié: (2025)