Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach
Paper • 2410.00025 • Published
AI & ML interests
CoML is based in the Departement d’Etudes Cognitives of the Ecole Normale Supérieure and is a joint EHESS, ENS, CNRS and Inria research team at the intersection between cognitive and computer science.
Recent Activity
View all activity
mpoli
authored 5
papers 10 days ago
fastabx: A library for efficient computation of ABX discriminability
Paper • 2505.02692 • Published
BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings
Paper • 2509.15001 • Published
SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision
Paper • 2512.20308 • Published
DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units
Paper • 2603.18612 • Published
mpoli
updated a
model 10 days ago
mpoli
updated a
collection 10 days ago
mpoli
published a
model 10 days ago
mpoli
updated a
model 10 days ago
mpoli
published a
model 10 days ago
mpoli
published 2
models 13 days ago
mpoli
updated 2
models 13 days ago
arxaqapi
updated a
model about 1 month ago
[bot] Conversion to Parquet
#1 opened about 1 month ago
by 
parquet-converter