Effects of Word Embeddings on Neural Network-based Pitch Accent Detection
This work addresses pitch accent detection for speech processing applications, but it is incremental as it builds on existing methods with a focus on feature analysis.
The study investigated the impact of incorporating word embeddings into a convolutional neural network for pitch accent detection, finding that while embeddings improved performance within the same dataset, they hindered generalization to unseen data across three English datasets.
Pitch accent detection often makes use of both acoustic and lexical features based on the fact that pitch accents tend to correlate with certain words. In this paper, we extend a pitch accent detector that involves a convolutional neural network to include word embeddings, which are state-of-the-art vector representations of words. We examine the effect these features have on within-corpus and cross-corpus experiments on three English datasets. The results show that while word embeddings can improve the performance in corpus-dependent experiments, they also have the potential to make generalization to unseen data more challenging.