Training and testing the TDNN-OPGRU acoustic model on English read and spontaneous speech
G.D. Genkov (TU Delft - Electrical Engineering, Mathematics and Computer Science)
S. Feng – Mentor (TU Delft - Multimedia Computing)
O.E. (Odette) Scharenborg – Graduation committee member (TU Delft - Multimedia Computing)
Catholijn Jonker – Coach (TU Delft - Interactive Intelligence)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Automatic phoneme recognition (APR) is the process of recognizing phonemes (spoken sounds) in a recording of speech. It can be used for any application requiring fast and accurate transcription, i.e. a courthouse. This research creates such a model using the TDNN-OPGRU architecture and trains it on two datasets of recorded English speech - "TIMIT" for prewritten sentences being read out (prepared/read speech) and "Buckeye" for recorded interviews (spontaneous speech). The results of the model are analyzed and compared to similar research. The main conclusion is that the results obtained do not exceed previous research and in some cases are considerably worse. The reasoning for that is also included.