Speech to Text
Barry deVille, Gurpreet Singh Bawa · 2021
Researchers have noted that audio files can be preprocessed into an unstructured data stream that can then be used in much the same way as a regular text corpus for analytic processing. To illustrate the speech-to-text-to-analytics process, this chapter presents a case study that processes consumer audio feedback. Apart from the categorical predictions made on the audio content that develops a rough persona of the feedback providers' demographics, further analysis can be made on the audio content. The audio feedback is converted to text, several text analytics models can be implemented and executed on the textual content. Since the audio data is consumer feedback, the chapter provides information on extracting the associated sentiment of the feedback and try to extract the latent topic of the discussion for the feedback received.