End-to-end acoustic modelling for phone recognition of young readers

by   Lucile Gelin, et al.

Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their body development, as well as the lack of available child speech data. Young readers speech additionally displays peculiarities, such as slow reading rate and presence of reading mistakes, that hardens the task. This work attempts to tackle the main challenges in phone acoustic modelling for young child speech with limited data, and improve understanding of strengths and weaknesses of a wide selection of model architectures in this domain. We find that transfer learning techniques are highly efficient on end-to-end architectures for adult-to-child adaptation with a small amount of child speech data. Through transfer learning, a Transformer model complemented with a Connectionist Temporal Classification (CTC) objective function, reaches a phone error rate of 28.1 relative, as well as other end-to-end architectures by more than 8.5 An analysis of the models' performance on two specific reading tasks (isolated words and sentences) is provided, showing the influence of the utterance length on attention-based and CTC-based models. The Transformer+CTC model displays an ability to better detect reading mistakes made by children, that can be attributed to the CTC objective function effectively constraining the attention mechanisms to be monotonic.



There are no comments yet.


page 13


End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study

A key desiderata for inclusive and accessible speech recognition technol...

Fusing information streams in end-to-end audio-visual speech recognition

End-to-end acoustic speech recognition has quickly gained widespread pop...

Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations

Children speech recognition is challenging mainly due to the inherent hi...

End-to-end Silent Speech Recognition with Acoustic Sensing

Silent speech interfaces (SSI) has been an exciting area of recent inter...

Deep Learning for Prominence Detection in Children's Read Speech

Expressive reading, considered the defining attribute of oral reading fl...

End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Layer-wise Transfer Learning

Whispering is an important mode of human speech, but no end-to-end recog...

Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection

Recent advances in Text-to-Speech (TTS) have improved quality and natura...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.