Imagen de Portada

Time vs. Layer: Locating Predictive Cues for Dysarthric Speech Descriptors in wav2vec 2.0

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Engert, Natalie, Wagner, Dominik, Riedhammer, Korbinian, Bocklet, Tobias
Formato:	Preprint
Publicado:	2026
Materias:	Sound
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition
por: Wagner, Dominik, et al.
Publicado: (2025)

Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0
por: Bayerl, Sebastian P., et al.
Publicado: (2022)

Optimized Self-supervised Training with BEST-RQ for Speech Recognition
por: Baumann, Ilja, et al.
Publicado: (2025)

Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models
por: Wagner, Dominik, et al.
Publicado: (2024)

Shared Multi-modal Embedding Space for Face-Voice Association
por: Simic, Christopher, et al.
Publicado: (2025)

Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models
por: Simic, Christopher, et al.
Publicado: (2025)

Large Language Models for Dysfluency Detection in Stuttered Speech
por: Wagner, Dominik, et al.
Publicado: (2024)

Automatic classification of stop realisation with wav2vec2.0
por: Tanner, James, et al.
Publicado: (2025)

WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion Recognition
por: Li, Feng, et al.
Publicado: (2024)

Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0
por: Wang, Zhiyong, et al.
Publicado: (2024)

vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders
por: Guo, Yiwei, et al.
Publicado: (2024)

Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks
por: Wagner, Dominik, et al.
Publicado: (2023)

Experimental Study: Enhancing Voice Spoofing Detection Models with wav2vec 2.0
por: Kang, Taein, et al.
Publicado: (2024)

Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
por: Zhu, Qiushi, et al.
Publicado: (2024)

Iterative refinement, not training objective, makes HuBERT behave differently from wav2vec 2.0
por: Huo, Robin, et al.
Publicado: (2025)

On the Cross-lingual Transferability of Pre-trained wav2vec2-based Models
por: Grosman, Jonatas, et al.
Publicado: (2025)

Infusing Acoustic Pause Context into Text-Based Dementia Assessment
por: Braun, Franziska, et al.
Publicado: (2024)

Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis
por: Leung, Wing-Zin, et al.
Publicado: (2024)

CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments
por: Attia, Ahmed Adel, et al.
Publicado: (2024)

Optimized Speculative Sampling for GPU Hardware Accelerators
por: Wagner, Dominik, et al.
Publicado: (2024)

Probing Whisper for Dysarthric Speech in Detection and Assessment
por: Yue, Zhengjun, et al.
Publicado: (2025)

Prototype-Based Disentanglement for Controllable Dysarthric Speech Synthesis
por: Wang, Haoshen, et al.
Publicado: (2026)

Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features
por: Freisinger, Steffen, et al.
Publicado: (2026)

Generalizing to Unseen Disaster Events: A Causal View
por: Seeberger, Philipp, et al.
Publicado: (2025)

Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech
por: de Groot, Dimme, et al.
Publicado: (2025)

DQ-Data2vec: Decoupling Quantization for Multilingual Speech Recognition
por: Shao, Qijie, et al.
Publicado: (2025)

On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifacts
por: Gulzar, Kashaf, et al.
Publicado: (2025)

Improved Dysarthric Speech to Text Conversion via TTS Personalization
por: Mihajlik, Péter, et al.
Publicado: (2025)

Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition
por: Wang, Huimeng, et al.
Publicado: (2025)

Zero- and One-Shot Data Augmentation for Sentence-Level Dysarthric Speech Recognition in Constrained Scenarios
por: Wang, Shiyao, et al.
Publicado: (2025)

DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
por: Chen, Xueyuan, et al.
Publicado: (2025)

Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
por: Xie, Xurong, et al.
Publicado: (2022)

wav2pos: Sound Source Localization using Masked Autoencoders
por: Berg, Axel, et al.
Publicado: (2024)

wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech
por: Le-Duc, Khai, et al.
Publicado: (2024)

Inappropriate Pause Detection In Dysarthric Speech Using Large-Scale Speech Recognition
por: Lee, Jeehyun, et al.
Publicado: (2024)

UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization
por: Wang, Yuejiao, et al.
Publicado: (2024)

Towards Temporally Explainable Dysarthric Speech Clarity Assessment
por: Park, Seohyun, et al.
Publicado: (2025)

Cross-Learning Fine-Tuning Strategy for Dysarthric Speech Recognition Via CDSD database
por: Xiao, Qing, et al.
Publicado: (2025)

Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching
por: Das, Shoutrik, et al.
Publicado: (2025)

A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition
por: Wang, Shiyao, et al.
Publicado: (2025)