Naturalization of Text by the Insertion of Pauses and Filler Words
This work addresses the need for more natural-sounding voice interactions in electronic systems, though it is incremental as it builds on existing text-to-speech techniques.
The paper tackles the problem of making computerized voices sound more natural by inserting pauses and filler words into text, using methods based on bigram frequency and recurrent neural networks, and finds through a blind survey that the output is comparable to natural speech.
In this article, we introduce a set of methods to naturalize text based on natural human speech. Voice-based interactions provide a natural way of interfacing with electronic systems and are seeing a widespread adaptation of late. These computerized voices can be naturalized to some degree by inserting pauses and filler words at appropriate positions. The first proposed text transformation method uses the frequency of bigrams in the training data to make appropriate insertions in the input sentence. It uses a probability distribution to choose the insertions from a set of all possible insertions. This method is fast and can be included before a Text-To-Speech module. The second method uses a Recurrent Neural Network to predict the next word to be inserted. It confirms the insertions given by the bigram method. Additionally, the degree of naturalization can be controlled in both these methods. On the conduction of a blind survey, we conclude that the output of these text transformation methods is comparable to natural speech.