The role of articulatory feature representation quality in a computational
model of human spoken-word recognition
Scharenborg, O., & Merkx, D.
The role of articulatory feature representation quality in a computational model of human spoken-word recognition. In Proceedings of the Machine Learning in Speech and Language Processing Workshop (MLSLP 2018)
Fine-Tracker is a speech-based model of human speech
recognition. While previous work has shown that Fine-Tracker
is successful at modelling aspects of human spoken-word
recognition, its speech recognition performance is not
comparable to that of human performance, possibly due to
suboptimal intermediate articulatory feature (AF)
representations. This study investigates the effect of improved
AF representations, obtained using a state-of-the-art deep
convolutional network, on Fine-Tracker’s simulation and
recognition performance: Although the improved AF quality
resulted in improved speech recognition; it, surprisingly, did
not lead to an improvement in Fine-Tracker’s simulation power.