Total: 4
This talk is a retrospective of speech and language processing as witnessed by the speaker during the last 50 years. From exploratory scientific beginnings that emphasized the discovery of how speech is produced and perceived by humans to today’s plethora of applications using our technology, our field has witnessed explosive growth. The talk will review the historical development of our community and some of the key technical ideas that have shaped our field. Some of the ideas were influenced by developments in other fields, while some of the developments in our field have been instrumental in key advances in other fields, such as optical character recognition and machine translation. Important developments include the source-filter model, digital signal processing, linear prediction, vector quantization, deep neural networks, and statistical modeling methods, especially hidden Markov models (HMMs), with primary applications to speech analysis, synthesis, coding, and recognition. The talk will be sprinkled with lessons learned in the importance of various factors in performing our research, and will be peppered with interesting tidbits about key moments in the development of our technology. The talk will end with a brief prospective peek at the next 50 years.
A unique and defining trait of human behavior is our ability to communicate through speech. The fundamental organizational principles of the neural circuits within speech brain areas are largely unknown. In this talk, I will present new results from our research on the functional organization of the human higher-order auditory cortex, known as Wernicke’s area. I will focus on how neural populations in the superior temporal lobe encode acoustic-phonetic representations of speech, and also how they integrate influences of linguistic context to achieve perceptual robustness.
The foundation for lifelong literacy is built through a child’s experience with language in the first five years. Integrating research from biological, psycholinguistic, and sociocultural perspectives, I will examine why millions of children fail to reach their developmental potential in the early years and enter school without a strong foundation for learning, resulting in enormous loss of human potential.
I show how natural language processing can help model the spread of innovation through scientific communities, with special focus on the history of speech and language processing, and the important role of interdisciplinarity.