Speech and Text Analysis

Hi friends,
please check this app I made for audio and text analysis, up to now it manages:

  • Audio Prosodic Analysis
  • Silence ans Speech Rate
  • Gender and Mood Identification
  • Audio Similarity
  • Audio Recognition and Transcription
  • Text Most Common Tokens
  • Key Words Extraction
  • Named Entity Recognition
  • Part of Speech Tagging
  • Sentiment Analysis
  • Wordcloud
  • Mendenhall Curve

I’m completing it and after that want to add a classifier that leverages the NER extraction.
Any kind of collaboration/suggestion is welcome.
Here the link (if you want subscribe to the channel)



Really amazing!!
I wonder if there would be a way of applying mood analysis to the speech sound directly coming from the system audio (no files).
Cheers, Milcent

Dear Milcent, many thanks!
I really don’t know if there is a way to process the audio signal in streaming (so real-time from the audio system). As you correctly got, prosodic analysis makes some calculation starting from the audio file. Anyway I think the best solution in terms of let’s say mood accuracy (or confidence) is having a cross-check using both audio and transcription files.