[ad_1]
Spotify has been granted a patent for a new technology that can suggest songs to users based on voice data analysis. The global audio and music streaming giant first applied for this patent in February 2018 and it was granted by the United States Patent and Trademark Office (USPTO) this month.
The patent describes technology that will be able to identify various personal traits like “emotional state” from users and suggest content based on this model. Spotify was previously granted another rather unpleasant patent that involved customizing users’ Spotify experiences based on their personality traits.
The patent is entitled “Identification of perceptual attributes from audio signals” describes a way to process audio signal input from users – including speech content and background noise – to identify playable content based on that input.
In the patent description, the Swedish audio and music streaming giant explains that “most media streaming apps include a feature that provides users with specific media recommendations“. A common approach used by Spotify to identify listeners’ musical tastes is to use basic information such as age or gender.
The new patent takes it a step further and uses voice recognition technology to “collect user flavor attributes“. The patented technology aims to detect “intonation, stress, rhythm, and so on“and combine with”acoustic information in the Markov model architecture is hidden” so that Spotify can classify the user’s mood as “happy, angry, sad, or neutral”.
Spotify details that the emotional state, gender, age, and accent of the speaker providing the sound are analyzed. The metadata collected by the technology will also indicate the number of people in the environment who input the audio signal.
All this metadata is collected and analyzed together with Spotify listeners”previous request,” “lhistory and ratings,” “links to related profiles such as the user’s friends or colleagues”, and “the music collection and/or library the user is in”.
According to Spotify’s patent filing, the output will be an audio output of music that matches your preferences, or a display of the next suggested music track that matches your preferences. The output may only provide recommendations on visual display.
Spotify has previously patented another technology that can recommend music to users based on their personality traits. This patent aims to classify users according to different personality models such as openness, agreeableness, extroversion, neuroticism, and conscientiousness. This type of categorization has raised some eyebrows due to the seemingly unappealing method of personality categorization used by Spotify.
The audio and music streaming giant is known for its algorithms that recommend new audio content to users. While Spotify’s new patent comes as no surprise, the effectiveness of the new technology’s problematic factors will only be known to users once it hits the market.
The reader should note that the company patents the technology that has been developed, but does not necessarily use the concept in the products it markets. Thus, we invite our readers to take Spotify’s latest patents and directions that show the company only as a possibility for the future.
[ad_2]
Source link