Fundamental Frequency Feature Normalization and Data Augmentation for Child Speech Recognition
This work addresses the lack of child speech data for ASR systems, which is important for educational technology, but it is incremental as it builds on existing adult speech models.
The paper tackled the problem of automatic speech recognition for young children by proposing feature normalization and data augmentation based on fundamental frequency, resulting in a 19.3% relative WER improvement and achieving the best reported WER on the OGI Kids' Speech Corpus.
Automatic speech recognition (ASR) systems for young children are needed due to the importance of age-appropriate educational technology. Because of the lack of publicly available young child speech data, feature extraction strategies such as feature normalization and data augmentation must be considered to successfully train child ASR systems. This study proposes a novel technique for child ASR using both feature normalization and data augmentation methods based on the relationship between formants and fundamental frequency ($f_o$). Both the $f_o$ feature normalization and data augmentation techniques are implemented as a frequency shift in the Mel domain. These techniques are evaluated on a child read speech ASR task. Child ASR systems are trained by adapting a BLSTM-based acoustic model trained on adult speech. Using both $f_o$ normalization and data augmentation results in a relative word error rate (WER) improvement of 19.3% over the baseline when tested on the OGI Kids' Speech Corpus, and the resulting child ASR system achieves the best WER currently reported on this corpus.