Read and spontaneous speech classification based on variance of GMM supervectors

This paper provides a novel method to classify spoken utterances into reading style or spontaneous style. Read/spontaneous speech classification is important for extracting data to train acoustic models for speech recognition from real data in which read speech and spontaneous speech samples are mixed. We analyzed 23,900 reading and 31,988 spontaneous utterances of 30 speakers and found that variance of GMM supervectors in several consecutive utterances can discriminate the reading and spontaneous styles and has less speaker-dependency. Based on this knowledge, our method uses variance of GMM supervectors to classify unknown consecutive utterances into reading style or spontaneous style. Experiments show that our technique can classify 5 consecutive utterances of unknown speakers with over 95% accuracy without any other lexical, phonetic, or prosodic features.