Classifying Spoken Location Names
Thunder Talk at 2:15PM EDT
This talk will highlight a problem such as classification of speech data where the expected spoken utterance is a location name, and how one can have a machine learn differences between utterances. Speech feature extraction and building a successful classification model will be discussed using open-source tools in Python, along with practical examples to demonstrate usage using pyAudioProcessing. https://github.com/jsingh811/pyAudioProcessing