Take the pledge to vote

For a better tommorow#AajSawaroApnaKal
  • I agree to receive emails from News18

  • I promise to vote in this year's elections no matter what the odds are.
  • Please check above checkbox.


Thank you for
taking the pledge

Vote responsibly as each vote counts
and makes a diffrence


Issued in public interest by HDFC Life. HDFC Life Insurance Company Limited (Formerly HDFC Standard Life Insurance Company Limited) (“HDFC Life”). CIN: L65110MH2000PLC128245, IRDAI Reg. No. 101 . The name/letters "HDFC" in the name/logo of the company belongs to Housing Development Finance Corporation Limited ("HDFC Limited") and is used by HDFC Life under an agreement entered into with HDFC Limited. ARN EU/04/19/13618
Powered by cricketnext logo
1-min read

Feeling Down? Deezer Can Find You The Perfect Playlist With Mood Detecting AI

Deezer researchers published a paper last week titled, "Music Mood Detection Based on Audio and lyrics with Deep Neural Net," documenting their development of an AI system detecting and classifying the mood of music tracks.

AFP Relaxnews

Updated:September 26, 2018, 9:56 AM IST
Feeling Down? Deezer Can Find You The Perfect Playlist With Mood Detecting AI
Deezer can find you the perfect playlist with mood detecting AI

In the world of Spotify playlists and YouTube auto play, music listeners are looking for streams that fit both their current mood and the intensity of the feeling. When you're feeling down, there's nothing worse than your sad song playlist being interrupted by nightclub summer bop; let's be real, not every time and place is the right one.

Deezer, an international internet music streaming service, has a team of researchers dedicated to understanding how machines recognize track moods and intensities to better service their seven million users. In their research, spotted by Venture Beat, the researchers determined that not only the instrumental presentation of a song is the cause of emotion arousal, but also the song lyrics. In fact, the study states that "both modalities are equally important."

The team uses a model depending on deep learning to identify the emotional correlations between 18,000 tracks based on valence and arousal values. The study states that this method is more effective than previous classical approaches, specifically in identifying arousal levels thanks to their analysis of the instrumentals and not just the lyrical content.

At the conclusion of this study, the research group opened doors leading to the deeper exploration of obscure content, which will require large sample sizes of so-far inexistent data. More databases will lead to better-understood correlations. For example, in addition to the tracks within a database being labeled with mood and intensity, there could be a tertiary category for the AI to analyze: ambiguity level. In the event that listeners experience the same song differently, the AI could be trained to still form different playlists for each individual based on its correlation with previously played content.

Music tailored to your mood in real-time is on its way. Soon, your computer may be able to find you music far better than you can whether it's a calm playlist of sad songs after a breakup or some bumping EDM to celebrate a graduation. In any case, searching yourself for that perfect playlist may soon be a thing of the past.

Read full article
Next Story
Next Story

Also Watch


Live TV

Countdown To Elections Results
  • 01 d
  • 12 h
  • 38 m
  • 09 s
To Assembly Elections 2018 Results