Edinburgh Research Explorer

Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationINTERSPEECH 2019: Proceedings of the 20th Annual Conference of the International Speech Communication Association (ISCA)
Place of PublicationGraz, Austria
Number of pages5
Publication statusAccepted/In press - 17 Jun 2019
EventInterspeech 2019 - Graz, Austria
Duration: 15 Sep 201919 Sep 2019
https://www.interspeech2019.org/

Conference

ConferenceInterspeech 2019
CountryAustria
CityGraz
Period15/09/1919/09/19
Internet address

Abstract

We investigate the automatic processing of child speech therapy sessions using ultrasound visual biofeedback, with a specific focus on complementing acoustic features with ultrasound images of the tongue for the tasks of speaker diarization and time-alignment of target words. For speaker diarization, we propose an ultrasound-based time-domain signal which we call estimated tongue activity. For word-alignment, we augment an acoustic model with low-dimensional representations of ultrasound images of the tongue, learned by a convolutional neural network. We conduct our experiments using the Ultrasuite repository of ultrasound and speech recordings for child speech therapy sessions. For both tasks, we observe that systems augmented with ultrasound data outperform corresponding systems using only the audio signal.

    Research areas

  • speech recognition, speaker diarization, ultrasound tongue imaging, speech therapy, child speech, Ultrasuite

Event

Interspeech 2019

15/09/1919/09/19

Graz, Austria

Event: Conference

ID: 98336031