Cover Image

Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ahadzi, Edem, Singh, Vishwanath Pratap, Kinnunen, Tomi, Hautamaki, Ville
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2Vec2.0 Based ASR
by: Singh, Vishwanath Pratap, et al.
Published: (2024)

Causal Analysis of ASR Errors for Children: Quantifying the Impact of Physiological, Cognitive, and Extrinsic Factors
by: Singh, Vishwanath Pratap, et al.
Published: (2025)

Causal Structure Discovery for Error Diagnostics of Children's ASR
by: Singh, Vishwanath Pratap, et al.
Published: (2025)

ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification
by: Singh, Vishwanath Pratap, et al.
Published: (2024)

Meta-Learning Approaches for Improving Detection of Unseen Speech Deepfakes
by: Kukanov, Ivan, et al.
Published: (2024)

Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning
by: Xuan, Xi, et al.
Published: (2026)

Kinship Verification Using Voice
by: Mishra, Jagabandhu, et al.
Published: (2026)

Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition
by: Eeckt, Steven Vander, et al.
Published: (2022)

Investigating the Potential of Multi-Stage Score Fusion in Spoofing-Aware Speaker Verification
by: Kurnaz, Oguzhan, et al.
Published: (2025)

Cyclostationarity Analysis as a Complement to Self-Supervised Representations for Speech Deepfake Detection
by: Hanilçi, Cemal, et al.
Published: (2026)

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
by: Chen, Haolin, et al.
Published: (2024)

Advancing Zero-Shot Open-Set Speech Deepfake Source Tracing
by: Chhibber, Manasi, et al.
Published: (2025)

Joint Optimization of ASV and CM tasks: BTUEF Team's Submission for WildSpoof Challenge
by: Kurnaz, Oguzhan, et al.
Published: (2026)

Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
by: Eeckt, Steven Vander, et al.
Published: (2022)

Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification
by: Kurnaz, Oğuzhan, et al.
Published: (2025)

Optimizing a-DCF for Spoofing-Robust Speaker Verification
by: Kurnaz, Oğuzhan, et al.
Published: (2024)

Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components
by: Mishra, Jagabandhu, et al.
Published: (2025)

Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
by: Trinh, Viet Anh, et al.
Published: (2022)

An Explainable Probabilistic Attribute Embedding Approach for Spoofed Speech Characterization
by: Chhibber, Manasi, et al.
Published: (2024)

I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
by: Erscoi, Lelia, et al.
Published: (2026)

Generalizable speech deepfake detection via meta-learned LoRA
by: Laakkonen, Janne, et al.
Published: (2025)

Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection
by: Laakkonen, Janne, et al.
Published: (2025)

Gradient weighting for speaker verification in extremely low Signal-to-Noise Ratio
by: Ma, Yi, et al.
Published: (2024)

Inverse-Hessian Regularization for Continual Learning in ASR
by: Eeckt, Steven Vander, et al.
Published: (2026)

Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis
by: Wang, Xin, et al.
Published: (2024)

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark
by: Xuan, Xi, et al.
Published: (2025)

ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization
by: Mehmood, Haaris, et al.
Published: (2025)

WST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection
by: Xuan, Xi, et al.
Published: (2026)

Efficient Rehearsal for Continual Learning in ASR via Singular Value Tuning
by: Eeckt, Steven Vander, et al.
Published: (2026)

Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models
by: Lu, Ke-Han, et al.
Published: (2025)

WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detection
by: Xuan, Xi, et al.
Published: (2025)

Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
by: Shim, Hye-jin, et al.
Published: (2024)

a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verification
by: Shim, Hye-jin, et al.
Published: (2024)

Generalizing Speaker Verification for Spoof Awareness in the Embedding Space
by: Liu, Xuechen, et al.
Published: (2024)

DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models
by: Li, Li, et al.
Published: (2026)

MDM-ASR: Bridging Accuracy and Efficiency in ASR with Diffusion-Based Non-Autoregressive Decoding
by: Yen, Hao, et al.
Published: (2026)

FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
by: Kim, Jongsuk, et al.
Published: (2025)

Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
by: Kong, YuXiang, et al.
Published: (2025)

Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment
by: Gogoi, Parismita, et al.
Published: (2025)

All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR
by: Moriya, Takafumi, et al.
Published: (2025)