CNN Encoding of Acoustic Parameters for Prominence Detection
This work addresses prominence detection for evaluating children's reading fluency, but it appears incremental as it builds on existing methods with new architectures.
The paper tackled the problem of detecting prominent words in children's oral reading using acoustic and linguistic features, replacing a random forest with an RNN and deep learning for feature extraction, but no concrete performance numbers were provided.
Expressive reading, considered the defining attribute of oral reading fluency, comprises the prosodic realization of phrasing and prominence. In the context of evaluating oral reading, it helps to establish the speaker's comprehension of the text. We consider a labeled dataset of children's reading recordings for the speaker-independent detection of prominent words using acoustic-prosodic and lexico-syntactic features. A previous well-tuned random forest ensemble predictor is replaced by an RNN sequence classifier to exploit potential context dependency across the longer utterance. Further, deep learning is applied to obtain word-level features from low-level acoustic contours of fundamental frequency, intensity and spectral shape in an end-to-end fashion. Performance comparisons are presented across the different feature types and across different feature learning architectures for prominent word prediction to draw insights wherever possible.