Skip to main content
. Author manuscript; available in PMC: 2021 Jul 22.
Published in final edited form as: Interspeech. 2018 Sep;2018:3413–3417. doi: 10.21437/interspeech.2018-2551

Figure 1:

Figure 1:

Data Pipeline. Left part shows data flow to get human transcribed utterance level data. Middle part shows the data flow to create similar data using automatic transcription. Right, shows pipeline for extracting prosodic features at the word level.