Speech Production Features for Deep Neural Network Acoustic Modeling - 2015
Offered By: Center for Language & Speech Processing(CLSP), JHU via YouTube
Course Description
Overview
Explore deep neural network acoustic modeling techniques incorporating speech production knowledge in this 55-minute lecture by Leonardo Badino from the Center for Language & Speech Processing at Johns Hopkins University. Delve into two approaches: using vocal tract movement measurements to extract new acoustic features, and deriving continuous-valued speech production knowledge features from binary phonological features to build structured DNN outputs. Examine the results of these methods tested on mngu0 and TIMIT datasets, showing consistent phone recognition error reduction. Learn about the speaker's background in speech technology and current research focus on speech production knowledge for automatic speech recognition, limited resources ASR, and computational analysis of non-verbal sensorimotor communication.
Syllabus
Intro
Speech production knowledge (SPK) for
Speech production knowledge for
An Example of the potential utility of using a measured Articulatory (+Acoustic) Domain
Motivations from neurophysiology of speech perception
Properties of the Acoustic-to-Articulatory Mapping
Autoencoders for AF transformation
Limitations of the approach
Alternative Approaches
Using Phonological Embeddings
Results - 2
Speaker-dependent phone recognition results-2 Mocha-timit, different noise conditions. Training on clean speech
Taught by
Center for Language & Speech Processing(CLSP), JHU
Related Courses
Miracles of Human Language: An Introduction to LinguisticsLeiden University via Coursera ภาษาศาสตร์เบื้องต้น | Introduction to Linguistics
Chiang Rai Rajabhat University via ThaiMOOC Phonetics And Phonology: A Broad Overview
Indian Institute of Technology Guwahati via Swayam Introduction to Modern Linguistics
NPTEL via YouTube Greek Lessons - A1 Level
YouTube