Spotify has been granted a patent for logo spanking new tech that could suggest songs to clients based mostly on the assessment of their voice data. The international audio and music streaming huge had first carried out for this patent in February 2018 and it was granted thru the US Patent and Trademark Office (USPTO) this month. The patent outlines tech proceeding to be able to select out out diverse personal developments like the “emotional state” of the clients and suggest content material cloth based mostly on this model. Spotify was earlier granted every other as an opportunity unsettling patent that involved curating a user’s Spotify experience based mostly on their personality developments.
The patent titled “Identification of taste attributes from an audio signal” describes a manner for processing an audio signal input from clients – in conjunction with speech content material cloth and historical past noise – to select out playable content material cloth based mostly on the input.
In the patent description, the Swedish audio and music streaming huge explain that “it’s the far commonplace location for a media streaming application to embody features that provide customized media recommendations to a user”. A commonplace location technique that Spotify employs to select out a listener’s music taste is thru using number one statistics like age or gender.
The new patent takes it a step beside and uses the voice recognition generation to “collect the taste attributes of a user”. The patented generation targets to hit upon the “intonation, stress, rhythm, and the likes of gadgets of speech” and combine it with “acoustic statistics interior a hidden Markov model architecture” so that Spotify with being able to categorize the user’s mood as “happy, angry, sad, or neutral”.
Spotify information that the emotional state, gender, age, and accent of the speaker presenting the voice is analyzed. The metadata accumulated thru the generation may even suggest the wide variety of people withinside the environment in which the audio signal is entered.
All this metadata is accumulated and analyzed together with a Spotify listener’s “previous requests,” “listening and rating history,” “links to associated profiles which consist of those of the user’s friends or colleagues”, and “the user’s cutting-edge music collection and/or library”.
According to the Spotify patent filing, the output might be the audio output of music just like the preferences, or a display of recommended next music tracks just like the preferences. The output also can be to truly provide recommendations on a seen display.
Spotify has earlier patented every other generation that could suggest music to clients based mostly on their personal developments. This patent aimed to categorize clients below neath certainly considered one among type personality models like openness, agreeableness, extroversion, neuroticism, and conscientiousness. This shape of categorization had raised some eyebrows because of the apparently unsettling personality categorization approach used by Spotify.
The audio and music streaming huge are ideas for its set of guidelines that indicate new audio content material cloth for its clients. While the modern-day Spotify patent could now no longer come as a surprise, the effectiveness of the complex factors that the modern-day generation includes will maximum correctly be identified to the clients if it hits the market.
Readers have to have a look at that group’s patent era they have conceptualized, however, won’t usually use the concept in a marketed product. Thus, we urge readers to take the contemporary Spotify patent and direction it elements the enterprise as the handiest a possibility for the future.
He is a fitness coach, musicologist and ethnomusicologist. He is a National Fitness Trainer, in Indonesia, and University Professor, Emeritus of the Department of Composition and Theory, the College of Music of the University of Jakarta Indonesia.