Arias Vergara, TomásArgüello Vélez, PatriciaVásquez Correa, Juan CamiloNöth, ElmarSchuster, Maria ElkeGonzález Rátiva, Marí­a ClaudiaOrozco Arroyave, Juan Rafael2020-10-232020-10-232020-05-271051-2004http://repositorio.usc.edu.co/handle/20.500.12421/4532Voice Onset Time (VOT) has been used by researchers as an acoustic measure in order to gain some understanding about the impact of different motor speech disorders in speech production. However, VOT values are usually obtained manually, which is expensive and time consuming. In this paper we proposed a method for the automatic detection of VOT based on pre-trained Recurrent Neural Networks with Gated Recurrent Units (GRUs). Speech recordings from 50 Spanish native speakers from Colombia (25 male) are considered for the experiments. The recordings include the utterance of the diadochokinesis task /pa-ta-ka/ which is typically used for the evaluation of motor speech disorders like those caused due to Parkinson's disease. Additionally, the diadochokinesis task allows us to train a system to detect the VOT of voiceless plosive sounds in intermediate positions. Acoustic analysis is performed by extracting different temporal and spectral features from the recordings. According to the results, it is possible to detect the VOT with F1-score values of 0.66 for Image 1, 0.75 for Image 2, and 0.78 for Image 3 when the predicted values are compared with respect to the manual VOT labels.enDiadochokinesisRecurrent neural networkVoice Onset TimeVoiceless stop consonantsArticle