Joined the team
Audio Analysis Challenge
(07) Retrieve as much information as possible from an audio collection, through various Machine Learning/Natural Language Processing methods
🌘🌗🌖🌕🌔🌓🌒 Team 7 is retrieving information from the audio collection "Radio Pleine Lune" through various machine learning & natural language processing methods > @AContestataires @memoriav_ch #GLAMhack2022 @supsi_ch // https://t.co/tGb1S7P3cB https://t.co/mKbJ34Pa8K pic.twitter.com/yh6JM1rItk— Opendata.ch (@OpendataCH@mastodon.social) (@OpendataCH) November 5, 2022
Retrieve as much information as possible from an audio collection, through various Machine Learning/Natural Language Processing methods:
- speech emotion recognition / sentiment analysis (from the transcription text or directly on audio, if doable): classify and tag speech/speakers’ sentiment based on their polarity (positive, negative, or neutral) or beyond (different emotions)
- eventually data visualizations based on the results (e.g., https://50-jahre-hitparade.ch/analysis/ - from where the chart above comes from)
Collection “Radio pleine lune”: Radio Pleine Lune, was a feminist radio program in the Geneva region that started with pirate broadcasts in 1979. The collection has been deposited in the Archives contestataires in Geneva, which collects, preserves, and valorizes documents from social movements of the second half of the 20th century. The program existed from 1980 to 1999. It is of particular importance for the Archives contestataires insofar as it gives an account of the various media forms used by protest movements in the second half of the 20th century. The materials represent broadcasts, thus direct recordings in the studio, as well as some rush documents, essentially interviews.
Information about the collection:
https://api.memobase.ch/record/advancedSearch?q=isPartOf:mbrs:acc-001 Metadata are in French. Most relevant fields are the title, the abstract and the keywords (hasSubject).
Data: 443 audio recordings.
- not enough training data
- chaotic corpus (multiple voices, live speaking)
Needs: developers with experience with audio analysis algorithms; eventually, web designers.
Edited content version 22
Edited content version 20
Testing different solutions for speech-to-text
Edited content version 16
Edited content version 14
Edited content version 12
Edited content version 8
Edited content version 6
Edited content version 4
Joined the team