Image de couverture de livre

Polynomial Mixing for Efficient Self-supervised Speech Encoders

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Feillet, Eva, Whetten, Ryan, Picard, David, Allauzen, Alexandre
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Open Implementation and Study of BEST-RQ for Speech Processing
par: Whetten, Ryan, et autres
Publié: (2024)

Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics
par: Colagrande, Alex, et autres
Publié: (2025)

Limits of Resolution Equivariance in Fourier Neural Operators
par: Colagrande, Alex, et autres
Publié: (2026)

Towards Early Prediction of Self-Supervised Speech Model Performance
par: Whetten, Ryan, et autres
Publié: (2025)

Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
par: Fagnou, Erwan, et autres
Publié: (2026)

Chain and Causal Attention for Efficient Entity Tracking
par: Fagnou, Erwan, et autres
Publié: (2024)

Exploring Precision and Recall to assess the quality and diversity of LLMs
par: Bronnec, Florian Le, et autres
Publié: (2024)

Improving Diversity in Language Models: When Temperature Fails, Change the Loss
par: Verine, Alexandre, et autres
Publié: (2025)

Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity
par: Zhao, Hangyue, et autres
Publié: (2026)

An Analysis of Linear Complexity Attention Substitutes with BEST-RQ
par: Whetten, Ryan, et autres
Publié: (2024)

TiME: Tiny Monolingual Encoders for Efficient NLP Pipelines
par: Schulmeister, David, et autres
Publié: (2025)

Efficient Sample-Specific Encoder Perturbations
par: Fathullah, Yassir, et autres
Publié: (2024)

Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model
par: Fang, Hung-Chieh, et autres
Publié: (2024)

[b]=[d]-[t]+[p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
par: Choi, Kwanghee, et autres
Publié: (2026)

Patent Representation Learning via Self-supervision
par: Zuo, You, et autres
Publié: (2025)

On Affine Homotopy between Language Encoders
par: Chan, Robin SM, et autres
Publié: (2024)

On Importance of Code-Mixed Embeddings for Hate Speech Identification
par: Jagdale, Shruti, et autres
Publié: (2024)

PoM: Efficient Image and Video Generation with the Polynomial Mixer
par: Picard, David, et autres
Publié: (2024)

Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications
par: Kudlur, Manjunath, et autres
Publié: (2026)

LOCOST: State-Space Models for Long Document Abstractive Summarization
par: Bronnec, Florian Le, et autres
Publié: (2024)

Where Do Self-Supervised Speech Models Become Unfair?
par: Herron, Felix, et autres
Publié: (2026)

Coupling Speech Encoders with Downstream Text Models
par: Chelba, Ciprian, et autres
Publié: (2024)

CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning
par: Bekhouche, Salah Eddine, et autres
Publié: (2025)

A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
par: van Niekerk, Carel, et autres
Publié: (2023)

Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models
par: Herron, Felix, et autres
Publié: (2026)

SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
par: Lamaakal, Ismail, et autres
Publié: (2025)

Recommendation of data-free class-incremental learning algorithms by simulating future data
par: Feillet, Eva, et autres
Publié: (2024)

Knowledge Graph Reasoning with Self-supervised Reinforcement Learning
par: Ma, Ying, et autres
Publié: (2024)

Progressive Mixed-Precision Decoding for Efficient LLM Inference
par: Chen, Hao Mark, et autres
Publié: (2024)

Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection
par: Eilertsen, Brage, et autres
Publié: (2025)

Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognition
par: Zhu, Wenjing, et autres
Publié: (2024)

Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition
par: Xu, Jingjing, et autres
Publié: (2024)

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
par: Jin, Rihui, et autres
Publié: (2025)

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
par: De, Soham, et autres
Publié: (2024)

Self-supervised learning of speech representations with Dutch archival data
par: Vaessen, Nik, et autres
Publié: (2025)

ENTP: Encoder-only Next Token Prediction
par: Ewer, Ethan, et autres
Publié: (2024)

NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data
par: Bogdanov, Sergei, et autres
Publié: (2024)

ChatGPT in Linear Algebra: Strides Forward, Steps to Go
par: Bagno, Eli, et autres
Publié: (2024)

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation
par: Duong, Song, et autres
Publié: (2025)

TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes
par: Jourdan, Fanny, et autres
Publié: (2023)