Modelling prosodic structure using Artificial Neural Networks
This work addresses a domain-specific challenge in automatic speech recognition for tonal languages, but it is incremental as it applies existing methods to a new dataset.
The paper tackled the problem of classifying Cypriot Greek questions and statements using neural networks, achieving 95% accuracy with a convolutional network that outperformed an LSTM.
The ability to accurately perceive whether a speaker is asking a question or is making a statement is crucial for any successful interaction. However, learning and classifying tonal patterns has been a challenging task for automatic speech recognition and for models of tonal representation, as tonal contours are characterized by significant variation. This paper provides a classification model of Cypriot Greek questions and statements. We evaluate two state-of-the-art network architectures: a Long Short-Term Memory (LSTM) network and a convolutional network (ConvNet). The ConvNet outperforms the LSTM in the classification task and exhibited an excellent performance with 95% classification accuracy.