Copertina

Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Vosoughi, Ali, Emmanouilidou, Dimitra, Gamper, Hannes
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Multimedia Computation and Language Information Retrieval Sound Audio and Speech Processing 68T, 68T45, 68T10
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can Sound Replace Vision in LLaVA With Token Substitution?
di: Vosoughi, Ali, et al.
Pubblicazione: (2025)

M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation
di: Niizumi, Daisuke, et al.
Pubblicazione: (2024)

Towards Multilingual Audio-Visual Question Answering
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation
di: Behera, Swarup Ranjan, et al.
Pubblicazione: (2024)

Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance
di: Li, Yuanchao, et al.
Pubblicazione: (2024)

Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localization
di: Wu, Junyan, et al.
Pubblicazione: (2024)

Comparative Analysis of Audio Feature Extraction for Real-Time Talking Portrait Synthesis
di: Salehi, Pegah, et al.
Pubblicazione: (2024)

Representation Loss Minimization with Randomized Selection Strategy for Efficient Environmental Fake Audio Detection
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning
di: Niizumi, Daisuke, et al.
Pubblicazione: (2026)

Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

Non-Verbal Vocalisations and their Challenges: Emotion, Privacy, Sparseness, and Real Life
di: Batliner, Anton, et al.
Pubblicazione: (2025)

Multi-View Multi-Task Modeling with Speech Foundation Models for Speech Forensic Tasks
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

ChordSync: Conformer-Based Alignment of Chord Annotations to Music Audio
di: Poltronieri, Andrea, et al.
Pubblicazione: (2024)

Avengers Assemble: Amalgamation of Non-Semantic Features for Depression Detection
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

SeQuiFi: Mitigating Catastrophic Forgetting in Speech Emotion Recognition with Sequential Class-Finetuning
di: Jain, Sarthak, et al.
Pubblicazione: (2024)

Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
di: Phukan, Orchid Chetia, et al.
Pubblicazione: (2024)

Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
di: Niizumi, Daisuke, et al.
Pubblicazione: (2024)

Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection
di: Niizumi, Daisuke, et al.
Pubblicazione: (2024)

Towards Pre-training an Effective Respiratory Audio Foundation Model
di: Niizumi, Daisuke, et al.
Pubblicazione: (2025)

MATER: Multi-level Acoustic and Textual Emotion Representation for Interpretable Speech Emotion Recognition
di: Jon, Hyo Jin, et al.
Pubblicazione: (2025)

Assessing the Utility of Audio Foundation Models for Heart and Respiratory Sound Analysis
di: Niizumi, Daisuke, et al.
Pubblicazione: (2025)

Faked Speech Detection with Zero Prior Knowledge
di: Ajmi, Sahar Al, et al.
Pubblicazione: (2022)

AI-based Drone Assisted Human Rescue in Disaster Environments: Challenges and Opportunities
di: Papyan, Narek, et al.
Pubblicazione: (2024)

A Speech Enhancement Method Using Fast Fourier Transform and Convolutional Autoencoder
di: Kow, Pu-Yun, et al.
Pubblicazione: (2025)

Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion Reasoning
di: Han, Zhiyuan, et al.
Pubblicazione: (2025)

Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment
di: Roy, Abhinaba, et al.
Pubblicazione: (2025)

A Unified Model For Voice and Accent Conversion In Speech and Singing using Self-Supervised Learning and Feature Extraction
di: Cheripally, Sowmya
Pubblicazione: (2024)

Recent Advances and Challenges in Deep Audio-Visual Correlation Learning
di: Vilaça, Luís, et al.
Pubblicazione: (2022)

AudioTime: A Temporally-aligned Audio-text Benchmark Dataset
di: Xie, Zeyu, et al.
Pubblicazione: (2024)

SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
di: Melechovsky, Jan, et al.
Pubblicazione: (2025)

PicoAudio2: Temporal Controllable Text-to-Audio Generation with Natural Language Description
di: Zheng, Zihao, et al.
Pubblicazione: (2025)

PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation
di: Xie, Zeyu, et al.
Pubblicazione: (2024)

PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset
di: Hou, Yang, et al.
Pubblicazione: (2024)

Learning Robust Spatial Representations from Binaural Audio through Feature Distillation
di: Bovbjerg, Holger Severin, et al.
Pubblicazione: (2025)

FakeSound: Deepfake General Audio Detection
di: Xie, Zeyu, et al.
Pubblicazione: (2024)

STAR: Speech-to-Audio Generation via Representation Learning
di: Xie, Zeyu, et al.
Pubblicazione: (2025)

Monaural Multi-Speaker Speech Separation Using Efficient Transformer Model
di: Rijal, S., et al.
Pubblicazione: (2023)

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding
di: Li, Bohan, et al.
Pubblicazione: (2024)

SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement
di: Chen, Kuan-Yu, et al.
Pubblicazione: (2025)