4 papers
Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection
Xinwei Cao, Mengxuan Lu, Torbjørn Svendsen +1
We address the problem of out-of-distribution (OOD) detection for target observations embedded in a subspace of the high dimensional data space. Using continuous normalizing flows…
Segmentation-free Goodness of Pronunciation
Xinwei Cao, Zijian Fan, Torbjørn Svendsen +1
Mispronunciation detection and diagnosis (MDD) is a significant part in modern computer-aided language learning (CALL) systems. Most systems implementing phoneme-level MDD through…
Non-native Children's Automatic Speech Assessment Challenge (NOCASA)
Yaroslav Getman, Tamás Grósz, Mikko Kurimo +1
This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to d…
S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction
Mohammad Adiban, Kalin Stefanov, Sabato Marco Siniscalchi +1
We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), an…