[video] Abstract For the last two hundred years, and especially for the last 60, primary accounts of illness experience written by patients have generated greater interest to help understand personal aspects of living and dealing[…]

Read More

[video] Abstract We present a new algorithm for efficiently training n-gram language models on uncertain data, and illustrate its use for semi-supervised language model adaptation. We compute the probability that an n-gram occurs k times[…]

Read More

[video] Abstract April C. Foreman, Ph.D., will discuss how natural language processing can be applied in different ways to the architecture of the mental health system. She will cover potential applications for symptom tracking, diagnosis,[…]

Read More

[video] Abstract The phonological class probabilities are the probabilities of individual phonological classes (known also as phonological or distinctive features) inferred from a short segment of speech signal. A vector of all phonological class probabilities[…]

Read More

ABSTRACT We will discuss recent studies demonstrating that computational analysis of transcribed spoken and written language can provide for highly accurate diagnostics over a wide variety of psychiatric and neurologic conditions such as psychosis, drug[…]

Read More

Abstract Traditional speech recognizers are built, deployed into production, and typically not updated until the next refresh.  This approach to speech recognition does not leverage all the contextual information available to the recognizer, such as[…]

Read More

Abstract Creative individuals have been consciously constructing languages since the 12th century. Prior to the 20th century, conlangers (language creators) had ulterior motives for creating language, be it to create a language for religious expression,[…]

Read More