Imagen de Portada

Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Perera, David, Letzelter, Victor, Mariotte, Théo, Cortés, Adrien, Chen, Mickael, Essid, Slim, Richard, Gaël
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Sound Audio and Speech Processing Probability
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multiple Choice Learning for Efficient Speech Separation with Many Speakers
por: Perera, David, et al.
Publicado: (2024)

Controlling Contrastive Self-Supervised Learning with Knowledge-Driven Multiple Hypothesis: Application to Beat Tracking
por: Gagnere, Antonin, et al.
Publicado: (2025)

Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations
por: Zaiem, Salah, et al.
Publicado: (2024)

A Contrastive Self-Supervised Learning scheme for beat tracking amenable to few-shot learning
por: Gagnere, Antonin, et al.
Publicado: (2024)

SALT: Standardized Audio event Label Taxonomy
por: Stamatiadis, Paraskevas, et al.
Publicado: (2024)

Winner-takes-all learners are geometry-aware conditional density estimators
por: Letzelter, Victor, et al.
Publicado: (2024)

A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification
por: Olvera, Michel, et al.
Publicado: (2024)

A lightweight dual-stage framework for personalized speech enhancement based on DeepFilterNet2
por: Serre, Thomas, et al.
Publicado: (2024)

Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detection
por: Mariotte, Théo, et al.
Publicado: (2024)

Contrastive Knowledge Distillation for Embedding Refinement in Personalized Speech Enhancement
por: Serre, Thomas, et al.
Publicado: (2026)

Perceptual Noise-Masking with Music through Deep Spectral Envelope Shaping
por: Berger, Clémentine, et al.
Publicado: (2025)

Online speaker diarization of meetings guided by speech separation
por: Gruttadauria, Elio, et al.
Publicado: (2024)

ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings
por: Mariotte, Theo, et al.
Publicado: (2024)

Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing
por: Lebourdais, Martin, et al.
Publicado: (2024)

IS${}^3$ : Generic Impulsive--Stationary Sound Separation in Acoustic Scenes using Deep Filtering
por: Berger, Clémentine, et al.
Publicado: (2025)

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads
por: Zaiem, Salah, et al.
Publicado: (2023)

WaveTransfer: A Flexible End-to-end Multi-instrument Timbre Transfer with Diffusion
por: Baoueb, Teysir, et al.
Publicado: (2024)

An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution Alignment
por: Malard, Hugo, et al.
Publicado: (2024)

Point Processes and spatial statistics in time-frequency analysis
por: Pascal, Barbara, et al.
Publicado: (2024)

An Explainable Proxy Model for Multiabel Audio Segmentation
por: Mariotte, Théo, et al.
Publicado: (2024)

Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems
por: Raymondaud, Quentin, et al.
Publicado: (2024)

Sparse Autoencoders Make Audio Foundation Models more Explainable
por: Mariotte, Théo, et al.
Publicado: (2025)

VAE-based Phoneme Alignment Using Gradient Annealing and SSL Acoustic Features
por: Koriyama, Tomoki
Publicado: (2024)

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

Singer Identity Representation Learning using Self-Supervised Techniques
por: Torres, Bernardo, et al.
Publicado: (2024)

Structure-informed Positional Encoding for Music Generation
por: Agarwal, Manvi, et al.
Publicado: (2024)

Déréverbération non-supervisée de la parole par modèle hybride
por: Bahrman, Louis, et al.
Publicado: (2025)

6KSFx Synth Dataset
por: Garcia, Nelly, et al.
Publicado: (2025)

Research on the Acoustic Emission Source Localization Methodology in Composite Materials based on Artificial Intelligence
por: Won, Jongick, et al.
Publicado: (2024)

SLAP: Learning Speaker and Health-Related Representations from Natural Language Supervision
por: Ando, Angelika, et al.
Publicado: (2025)

Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models
por: Miara, Victor, et al.
Publicado: (2024)

Désentrelacement Fréquentiel Doux pour les Codecs Audio Neuronaux
por: Giniès, Benoît, et al.
Publicado: (2025)

Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2
por: Bousquet, Pierre-Michel, et al.
Publicado: (2024)

Spatial Reverberation and Dereverberation using an Acoustic Multiple-Input Multiple-Output System
por: Morgenstern, Hai, et al.
Publicado: (2024)

Speech dereverberation constrained on room impulse response characteristics
por: Bahrman, Louis, et al.
Publicado: (2024)

On Speaker Attribution with SURT
por: Raj, Desh, et al.
Publicado: (2024)

Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection
por: Stourbe, Theophile, et al.
Publicado: (2024)

MSP-Podcast SER Challenge 2024: L'antenne du Ventoux Multimodal Self-Supervised Learning for Speech Emotion Recognition
por: Duret, Jarod, et al.
Publicado: (2024)

Multilingual Turn-taking Prediction Using Voice Activity Projection
por: Inoue, Koji, et al.
Publicado: (2024)

Visual Cues Support Robust Turn-taking Prediction in Noise
por: Russell, Sam O'Connor, et al.
Publicado: (2025)