Buchumschlag

DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lin, Tzu-Quan, Lee, Hung-yi, Tang, Hao
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Sound Artificial Intelligence Machine Learning Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Property Neurons in Self-Supervised Speech Transformers
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2024)

Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2025)

Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2022)

MelHuBERT: A simplified HuBERT on Mel spectrograms
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2022)

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
von: Fu, Szu-Wei, et al.
Veröffentlicht: (2024)

Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction
von: Mu, Zhaoxi, et al.
Veröffentlicht: (2023)

Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
von: Ioannides, Georgios, et al.
Veröffentlicht: (2026)

Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
von: Liu, Andy T., et al.
Veröffentlicht: (2024)

From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2025)

DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
von: Cho, Deok-Hyeon, et al.
Veröffentlicht: (2025)

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

Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models
von: Shah, Neil, et al.
Veröffentlicht: (2024)

Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning
von: Medin, Lucas Block, et al.
Veröffentlicht: (2025)

CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning
von: Luong, Justin, et al.
Veröffentlicht: (2025)

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
von: Bradshaw, Louis, et al.
Veröffentlicht: (2025)

Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation
von: Ruggiero, Giuseppe, et al.
Veröffentlicht: (2025)

Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
von: Zhou, Yizhi, et al.
Veröffentlicht: (2025)

ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
von: Hsiao, Chi-Yuan, et al.
Veröffentlicht: (2026)

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation
von: Chen, Szu-Chi, et al.
Veröffentlicht: (2026)

AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2026)

EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning
von: Seth, Ashish, et al.
Veröffentlicht: (2024)

Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
von: Lin, Guan-Ting, et al.
Veröffentlicht: (2024)

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
von: Ioannides, Georgios, et al.
Veröffentlicht: (2025)

Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition
von: Su, Hsuan, et al.
Veröffentlicht: (2024)

Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning
von: Wu, Haibin, et al.
Veröffentlicht: (2021)

SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR
von: Huang, Wei-Ping, et al.
Veröffentlicht: (2025)

Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables
von: Attia, Ahmed Adel, et al.
Veröffentlicht: (2023)

Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations
von: Yadav, Sarthak, et al.
Veröffentlicht: (2024)

Bridging ASR and LLMs for Dysarthric Speech Recognition: Benchmarking Self-Supervised and Generative Approaches
von: Aboeitta, Ahmed, et al.
Veröffentlicht: (2025)

Knowing When to Quit: Probabilistic Early Exits for Speech Separation
von: Olsen, Kenny Falkær, et al.
Veröffentlicht: (2025)

Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models
von: Kuan, Chun-Yi, et al.
Veröffentlicht: (2026)

SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification
von: Lepage, Theo, et al.
Veröffentlicht: (2025)

Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech
von: Li, Yuxin, et al.
Veröffentlicht: (2025)

Facial Expression-Enhanced TTS: Combining Face Representation and Emotion Intensity for Adaptive Speech
von: Chu, Yunji, et al.
Veröffentlicht: (2024)

Enhancing Speech Emotion Recognition through Segmental Average Pooling of Self-Supervised Learning Features
von: Hyeon, Jonghwan, et al.
Veröffentlicht: (2024)

Adaptive Duration Model for Text Speech Alignment
von: Cao, Junjie
Veröffentlicht: (2025)

CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
von: Wu, Haibin, et al.
Veröffentlicht: (2024)

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
von: Yang, Chih-Kai, et al.
Veröffentlicht: (2025)

How Contrastive Decoding Enhances Large Audio Language Models?
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2026)

SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
von: Hsu, Ming-Hao, et al.
Veröffentlicht: (2024)