Imagen de Portada

Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Xuanru, Shao, Yiwen, Tseng, Wei-Cheng, Yu, Dong
Formato:	Preprint
Publicado:	2026
Materias:	Sound Artificial Intelligence Audio and Speech Processing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding
por: Huo, Mingyue, et al.
Publicado: (2025)

Natural Language Supervision for General-Purpose Audio Representations
por: Elizalde, Benjamin, et al.
Publicado: (2023)

Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation
por: Tseng, Wei-Cheng, et al.
Publicado: (2025)

Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
por: Poncelet, Jakob, et al.
Publicado: (2021)

ProLAP: Probabilistic Language-Audio Pre-Training
por: Manabe, Toranosuke, et al.
Publicado: (2025)

OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
por: Bharadwaj, Shikhar, et al.
Publicado: (2025)

w2v-SELD: A Sound Event Localization and Detection Framework for Self-Supervised Spatial Audio Pre-Training
por: Santos, Orlem Lima dos, et al.
Publicado: (2023)

SRC-gAudio: Sampling-Rate-Controlled Audio Generation
por: Li, Chenxing, et al.
Publicado: (2024)

Effective Pre-Training of Audio Transformers for Sound Event Detection
por: Schmid, Florian, et al.
Publicado: (2024)

Efficient Scaling for LLM-based ASR
por: Mu, Bingshen, et al.
Publicado: (2025)

Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion
por: Li, Ruiqi, et al.
Publicado: (2024)

SemanticAudio: Audio Generation and Editing in Semantic Space
por: Dai, Zheqi, et al.
Publicado: (2026)

BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data
por: Xu, Xuenan, et al.
Publicado: (2023)

MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning
por: Zhao, Hang, et al.
Publicado: (2024)

MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events
por: Yang, Xiaoyu, et al.
Publicado: (2024)

Exploring Self-Supervised Audio Models for Generalized Anomalous Sound Detection
por: Han, Bing, et al.
Publicado: (2025)

AudioGenie-Reasoner: A Training-Free Multi-Agent Framework for Coarse-to-Fine Audio Deep Reasoning
por: Rong, Yan, et al.
Publicado: (2025)

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

Towards Weakly Supervised Text-to-Audio Grounding
por: Xu, Xuenan, et al.
Publicado: (2024)

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
por: Lu, Ke-Han, et al.
Publicado: (2025)

AudioEval: Automatic Dual-Perspective and Multi-Dimensional Evaluation of Text-to-Audio-Generation
por: Wang, Hui, et al.
Publicado: (2025)

Probing the Robustness Properties of Neural Speech Codecs
por: Tseng, Wei-Cheng, et al.
Publicado: (2025)

AudioLCM: Text-to-Audio Generation with Latent Consistency Models
por: Liu, Huadai, et al.
Publicado: (2024)

Video-to-Audio Generation with Fine-grained Temporal Semantics
por: Hu, Yuchen, et al.
Publicado: (2024)

EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
por: Hai, Jiarui, et al.
Publicado: (2024)

Temporal Pooling Strategies for Training-Free Anomalous Sound Detection with Self-Supervised Audio Embeddings
por: Wilkinghoff, Kevin, et al.
Publicado: (2026)

Unlocking Large Audio-Language Models for Interactive Language Learning
por: Liu, Hongfu, et al.
Publicado: (2026)

FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation
por: Liu, Huadai, et al.
Publicado: (2024)

DSCLAP: Domain-Specific Contrastive Language-Audio Pre-Training
por: Liu, Shengqiang, et al.
Publicado: (2024)

Leveraging Self-supervised Audio Representations for Data-Efficient Acoustic Scene Classification
por: Cai, Yiqiang, et al.
Publicado: (2024)

SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation
por: Zhang, Yizhou, et al.
Publicado: (2025)

UniAudio: An Audio Foundation Model Toward Universal Audio Generation
por: Yang, Dongchao, et al.
Publicado: (2023)

Audio-Language Models for Audio-Centric Tasks: A Systematic Survey
por: Su, Yi, et al.
Publicado: (2025)

CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
por: Wu, Haibin, et al.
Publicado: (2024)

Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
por: Xiao, Yang, et al.
Publicado: (2026)

AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning
por: Shao, Yiwen, et al.
Publicado: (2025)

Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification
por: Dawn, Aditya, et al.
Publicado: (2024)

MiDashengLM: Efficient Audio Understanding with General Audio Captions
por: Dinkel, Heinrich, et al.
Publicado: (2025)

AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework
por: Jia, Yuhang, et al.
Publicado: (2024)

Robust Audio Tagging under Class-wise Supervision Unreliability
por: Hou, Yuanbo, et al.
Publicado: (2026)