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

## TL;DR

This paper explores the use of ultrasound tongue imaging to improve speaker diarization and word alignment in child speech therapy sessions, demonstrating that ultrasound data enhances performance over audio-only methods.

## Contribution

It introduces ultrasound-based features for diarization and alignment, combining ultrasound images with acoustic data using neural networks, a novel approach in child speech therapy analysis.

## Key findings

- Ultrasound data improves diarization accuracy.
- Ultrasound enhances word alignment precision.
- Systems with ultrasound outperform audio-only models.

## 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.