38 citations · 74 across the 10 of their papers we have counts for
6 papers · 1 filter
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…
Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions
Moreno La Quatra, Maria Francesca Turco, Torbjørn Svendsen +3
This work is concerned with devising a robust Parkinson's (PD) disease detector from speech in real-world operating conditions using (i) foundational models, and (ii) speech enhanc…
Developing Acoustic Models for Automatic Speech Recognition in Swedish
Giampiero Salvi
This paper is concerned with automatic continuous speech recognition using trainable systems. The aim of this work is to build acoustic models for spoken Swedish. This is done empl…
Dynamic Behaviour of Connectionist Speech Recognition with Strong Latency Constraints
Giampiero Salvi
This paper describes the use of connectionist techniques in phonetic speech recognition with strong latency constraints. The constraints are imposed by the task of deriving the lip…
Segment Boundary Detection via Class Entropy Measurements in Connectionist Phoneme Recognition
Giampiero Salvi
This article investigates the possibility to use the class entropy of the output of a connectionist phoneme recogniser to predict time boundaries between phonetic classes. The rati…