Imagen de Portada

Evaluating Semantic Fragility in Text-to-Audio Generation Systems Under Controlled Prompt Perturbations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Wu, Jiahui
Formato:	Preprint
Publicado:	2026
Materias:	Sound Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows
por: Li, Xiquan, et al.
Publicado: (2025)

Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance
por: Zhang, Yaoyun, et al.
Publicado: (2024)

Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation
por: Xiong, Chenxu, et al.
Publicado: (2024)

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
por: Xie, Tianxin, et al.
Publicado: (2025)

AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
por: Kuan, Chun-Yi, et al.
Publicado: (2026)

Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning
por: Tsai, Fang-Duo, et al.
Publicado: (2024)

Generalizable Prompt Tuning for Audio-Language Models via Semantic Expansion
por: Jang, Jaehyuk, et al.
Publicado: (2026)

SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
por: Luo, Jiehui, et al.
Publicado: (2025)

ATIR: Towards Audio-Text Interleaved Contextual Retrieval
por: Zhao, Tong, et al.
Publicado: (2026)

AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion
por: Zhao, Junqi, et al.
Publicado: (2025)

DreamAudio: Customized Text-to-Audio Generation with Diffusion Models
por: Yuan, Yi, et al.
Publicado: (2025)

Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt
por: Shi, Yanfeng, et al.
Publicado: (2026)

AudioMotionBench: Evaluating Auditory Motion Perception in Audio LLMs
por: Sun, Zhe, et al.
Publicado: (2025)

ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation
por: Sun, Jiahui, et al.
Publicado: (2025)

FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation
por: Jiang, Yuxuan, et al.
Publicado: (2025)

Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis
por: Cui, Shuyang, et al.
Publicado: (2026)

AudioMoG: Guiding Audio Generation with Mixture-of-Guidance
por: Wang, Junyou, et al.
Publicado: (2025)

Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification
por: Ronchini, Francesca, et al.
Publicado: (2025)

DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer
por: Liu, Yisu, et al.
Publicado: (2025)

Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards
por: Fang, Linghan, et al.
Publicado: (2026)

AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech
por: Qiu, Jielin, et al.
Publicado: (2026)

AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation
por: Wang, Lu, et al.
Publicado: (2025)

RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing
por: Gao, Liting, et al.
Publicado: (2025)

Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception
por: Xie, Yuankun, et al.
Publicado: (2025)

Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding
por: Wang, Tsai-Ning, et al.
Publicado: (2025)

Retrieval-Augmented Text-to-Audio Generation
por: Yuan, Yi, et al.
Publicado: (2023)

Evaluation of Audio Language Models for Fairness, Safety, and Security
por: Aloufi, Ranya, et al.
Publicado: (2026)

Audio ControlNet for Fine-Grained Audio Generation and Editing
por: Zhu, Haina, et al.
Publicado: (2026)

Eureka-Audio: Triggering Audio Intelligence in Compact Language Models
por: Zhang, Dan, et al.
Publicado: (2026)

TTMBA: Towards Text To Multiple Sources Binaural Audio Generation
por: He, Yuxuan, et al.
Publicado: (2025)

All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation
por: Foo, Leonardo Haw-Yang, et al.
Publicado: (2026)

LoSATok: Low-dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation
por: Zhang, Zhisheng, et al.
Publicado: (2026)

Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
por: Lee, Junwon, et al.
Publicado: (2024)

AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
por: Xie, Yuankun, et al.
Publicado: (2026)

Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels
por: Weng, Yuzhe, et al.
Publicado: (2026)

In-the-wild Audio Spatialization with Flexible Text-guided Localization
por: Pan, Tianrui, et al.
Publicado: (2025)

AudioGenX: Explainability on Text-to-Audio Generative Models
por: Kang, Hyunju, et al.
Publicado: (2025)

ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling
por: Jiang, Yuxuan, et al.
Publicado: (2025)

VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories
por: Zhang, Qian, et al.
Publicado: (2026)

Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering
por: Glazer, Neta, et al.
Publicado: (2026)