Imagen de Portada

ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mehmood, Haaris, Saravanan, Karthikeyan, Parada, Pablo Peso, Tuckey, David, Ozay, Mete, Lee, Gil Ho, Lee, Jungin, Jung, Seokyeong
Formato:	Preprint
Publicado:	2025
Materias:	Audio and Speech Processing Sound
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Consistency Based Unsupervised Self-training For ASR Personalisation
por: Zhang, Jisi, et al.
Publicado: (2024)

persoDA: Personalized Data Augmentation for Personalized ASR
por: Parada, Pablo Peso, et al.
Publicado: (2025)

Locality enhanced dynamic biasing and sampling strategies for contextual ASR
por: Jalal, Md Asif, et al.
Publicado: (2024)

Retrieval Augmented Generation based context discovery for ASR
por: Siskos, Dimitrios, et al.
Publicado: (2025)

DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation
por: Xu, Jie, et al.
Publicado: (2024)

Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning
por: Zhang, Jisi, et al.
Publicado: (2025)

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
por: Mehmood, Haaris, et al.
Publicado: (2026)

Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
por: Xu, Jie, et al.
Publicado: (2026)

FlowW2N: Whispered-to-Normal Speech Conversion via Flow-Matching
por: Ritter-Gutierrez, Fabian, et al.
Publicado: (2026)

A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization
por: Fish, Edward, et al.
Publicado: (2023)

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
por: Mehmood, Haaris, et al.
Publicado: (2026)

Exploring compressibility of transformer based text-to-music (TTM) models
por: Moschopoulos, Vasileios, et al.
Publicado: (2024)

Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
por: Jung, Yeonjoon, et al.
Publicado: (2024)

Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence
por: Ahadzi, Edem, et al.
Publicado: (2025)

Sub-band Domain Multi-Hypothesis Acoustic Echo Canceler Based Acoustic Scene Analysis
por: Southwell, Benjamin J, et al.
Publicado: (2025)

ASR for Affective Speech: Investigating Impact of Emotion and Speech Generative Strategy
por: Wu, Ya-Tse, et al.
Publicado: (2026)

Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
por: Zhou, Rui, et al.
Publicado: (2024)

LUPET: Incorporating Hierarchical Information Path into Multilingual ASR
por: Liu, Wei, et al.
Publicado: (2024)

Learn and Don't Forget: Adding a New Language to ASR Foundation Models
por: Qian, Mengjie, et al.
Publicado: (2024)

Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches
por: Mujtaba, Dena, et al.
Publicado: (2025)

ManWav: The First Manchu ASR Model
por: Seo, Jean, et al.
Publicado: (2024)

A Bottom-up Framework with Language-universal Speech Attribute Modeling for Syllable-based ASR
por: Yen, Hao, et al.
Publicado: (2025)

AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration
por: Lee, Chia-Yu, et al.
Publicado: (2026)

A Parameter-efficient Language Extension Framework for Multilingual ASR
por: Liu, Wei, et al.
Publicado: (2024)

Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades
por: Jung, Donghyuk, et al.
Publicado: (2026)

HydraFormer: One Encoder For All Subsampling Rates
por: Xu, Yaoxun, et al.
Publicado: (2024)

SAM: A Mamba-2 State-Space Audio-Language Model
por: Lee, Taehan, et al.
Publicado: (2025)

Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling
por: Huang, Shao-Syuan, et al.
Publicado: (2024)

Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR
por: Lee, Jaeyoung, et al.
Publicado: (2026)

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

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models
por: Hsiao, Chi-Yuan, et al.
Publicado: (2025)

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
por: Tseng, Liang-Hsuan, et al.
Publicado: (2024)

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

Microphone Occlusion Mitigation for Own-Voice Enhancement in Head-Worn Microphone Arrays Using Switching-Adaptive Beamforming
por: Middelberg, Wiebke, et al.
Publicado: (2025)

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

CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
por: Shakeel, Muhammad, et al.
Publicado: (2026)

Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation
por: Yamashita, Natsuo, et al.
Publicado: (2026)

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

Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages
por: Cheng, Yao-Fei, et al.
Publicado: (2024)

LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration
por: Lee, Sangmin, et al.
Publicado: (2024)