Buchumschlag

Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zaiem, Salah, Parcollet, Titouan, Essid, Slim
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Audio and Speech Processing Sound
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

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

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

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

SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding
von: Parcollet, Titouan, et al.
Veröffentlicht: (2023)

Position-invariant Fine-tuning of Speech Enhancement Models with Self-supervised Speech Representations
von: Meghanani, Amit, et al.
Veröffentlicht: (2026)

Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation
von: Duret, Jarod, et al.
Veröffentlicht: (2024)

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

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

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

Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition
von: Parcollet, Titouan, et al.
Veröffentlicht: (2024)

Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
von: Parcollet, Titouan, et al.
Veröffentlicht: (2025)

Towards Early Prediction of Self-Supervised Speech Model Performance
von: Whetten, Ryan, et al.
Veröffentlicht: (2025)

SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations
von: Meghanani, Amit, et al.
Veröffentlicht: (2024)

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

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

ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations
von: Gong, Cheng, et al.
Veröffentlicht: (2023)

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

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

Self-supervised Multimodal Speech Representations for the Assessment of Schizophrenia Symptoms
von: Premananth, Gowtham, et al.
Veröffentlicht: (2024)

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

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
von: Ding, Shaojin, et al.
Veröffentlicht: (2023)

Probing Self-supervised Learning Models with Target Speech Extraction
von: Peng, Junyi, et al.
Veröffentlicht: (2024)

MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model
von: Shi, Jiatong, et al.
Veröffentlicht: (2024)

Target Speech Extraction with Pre-trained Self-supervised Learning Models
von: Peng, Junyi, et al.
Veröffentlicht: (2024)

From Sharpness to Better Generalization for Speech Deepfake Detection
von: Huang, Wen, et al.
Veröffentlicht: (2025)

LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
von: Parcollet, Titouan, et al.
Veröffentlicht: (2023)

SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition
von: Luo, Longjie, et al.
Veröffentlicht: (2025)

NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks
von: Huang, He, et al.
Veröffentlicht: (2024)

Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features
von: Tsunoo, Emiru, et al.
Veröffentlicht: (2024)

Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning
von: Cai, Danwei, et al.
Veröffentlicht: (2024)

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
von: Wang, Huimeng, et al.
Veröffentlicht: (2024)

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

Fusion of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition
von: Wang, Shih-heng, et al.
Veröffentlicht: (2024)

Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of Speech
von: Liang, Xinyu, et al.
Veröffentlicht: (2025)

Self-supervised Speech Representations Still Struggle with African American Vernacular English
von: Chang, Kalvin, et al.
Veröffentlicht: (2024)

SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition
von: Xue, Hongfei, et al.
Veröffentlicht: (2023)

Machine Unlearning in Speech Emotion Recognition via Forget Set Alone
von: Ren, Zhao, et al.
Veröffentlicht: (2025)

Fine-Grained Quantitative Emotion Editing for Speech Generation
von: Inoue, Sho, et al.
Veröffentlicht: (2024)

Less is More: Data Curation Matters in Scaling Speech Enhancement
von: Li, Chenda, et al.
Veröffentlicht: (2025)