Findings of the VarDial evaluation campaign 2023

N Aepli, Ç Çöltekin, R Van Der Goot… - arxiv preprint arxiv …, 2023 - arxiv.org
This report presents the results of the shared tasks organized as part of the VarDial
Evaluation Campaign 2023. The campaign is part of the tenth workshop on Natural …

A Compact End-to-End Model with Local and Global Context for Spoken Language Identification

F Jia, NR Koluguri, J Balam, B Ginsburg - arxiv preprint arxiv:2210.15781, 2022 - arxiv.org
We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language
Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D …

Efficiency-oriented approaches for self-supervised speech representation learning

L Lugo, V Vielzeuf - International Journal of Speech Technology, 2024 - Springer
Self-supervised learning enables the training of large neural models without the need for
large, labeled datasets. It has been generating breakthroughs in several fields, including …

LIFA: Language identification from audio with LPCC-G features

H Mukherjee, A Dhar, SM Obaidullah… - Multimedia Tools and …, 2024 - Springer
In Western countries, speech recognition-based technologies have significantly developed
compared to the countries of the South Asian subcontinent like India. India is a multilingual …

Exploring rhythm formant analysis for Indic language classification

P Gogoi, S Kalita, P Sarmah, SRM Prasanna - arxiv preprint arxiv …, 2024 - arxiv.org
This paper reports a preliminary study on quantitative frequency domain rhythm cues for
classifying five Indian languages: Bengali, Kannada, Malayalam, Marathi, and Tamil. We …

CA-SSLR: Condition-aware self-supervised learning representation for generalized speech processing

YJ Lu, J Liu, T Thebaud… - Advances in …, 2025 - proceedings.neurips.cc
Abstract We introduce Condition-Aware Self-Supervised Learning Representation (CA-
SSLR), a generalist conditioning model broadly applicable to various speech-processing …