Speaker-independent classification of phonetic segments from raw ultrasound in child speech
arXiv:1907.01413 · doi:10.1109/ICASSP.2019.8683564
Abstract
Ultrasound tongue imaging (UTI) provides a convenient way to visualize the vocal tract during speech production. UTI is increasingly being used for speech therapy, making it important to develop automatic methods to assist various time-consuming manual tasks currently performed by speech therapists. A key challenge is to generalize the automatic processing of ultrasound tongue images to previously unseen speakers. In this work, we investigate the classification of phonetic segments (tongue shapes) from raw ultrasound recordings under several training scenarios: speaker-dependent, multi-speaker, speaker-independent, and speaker-adapted. We observe that models underperform when applied to data from speakers not seen at training time. However, when provided with minimal additional speaker information, such as the mean ultrasound frame, the models generalize better to unseen speakers.
5 pages, 4 figures, published in ICASSP2019 (IEEE International Conference on Acoustics, Speech and Signal Processing, 2019)
References in corpus (1)
Cited by in corpus (4)
- Exploiting ultrasound tongue imaging for the automatic detection of speech articulation errors
- Automatic audiovisual synchronisation for ultrasound tongue imaging
- Automated Classification of Phonetic Segments in Child Speech Using Raw Ultrasound Imaging
- Convolutional Neural Network-Based Age Estimation Using B-Mode Ultrasound Tongue Image