Spotify patents a voice assistant capable of reading your emotions
Spotify appears to be interested in challenging Alexa and Siri with its own cutting edge voice assistant. Last month, the streaming service obtained a patent on new ways to make a voice assistant more responsive to human emotions.
Initially filed in 2018, the patent describes a voice assistant for a “media playback device” which could, for example, recognize when a user seems sad and recognize sympathetically (“you look a little depressed“), offer encouragement (“comfort”) or hard love (“regain consciousness!”). If a user seems in a hurry, the voice assistant may try to keep pace by speaking faster or responding in fewer words.
The theoretical voice assistant could listen to a user’s vocalized reactions to music and stop playing songs that seem to evoke anger, sadness, or other negative emotions.
“The Spotify patent … claims to interpret the emotion conveyed by human voice commands as part of the input, in the utterance itself, and apply intelligence to derive a logical result that cannot – not been explicitly requested, “said Simon Forrest, senior chief technology officer. analyst at Futuresource Consulting.
“One example is that the user says ‘ugh’ when a song starts playing and the voice assistant recognizes that this involves a negative emotional response and stops playing, or skips to another song, even though no ‘stop’ Or “jump” specific “The command has been issued,” Forrest said.
The technology described in the Spotify patent is said to be able to discern emotions from the tone, cadence, volume and pitch of a user’s voice. However, Spotify’s current capabilities in recognizing vocal emotions are unknown.
Rahul Telang, professor of information and management systems at Heinz College at Carnegie Mellon University, said recognition of speech emotions was still in its infancy.
“It’s an emerging field; I don’t think there is anything widely used in the market today, ”Telang said. “Two or three years later, it might become mainstream.”
Amazon and Google have also issued patents related to voice emotion recognition in recent years, as global sales of their smart speakers have increased. jumped. Last year, Bloomberg reported that Amazon was working on a voice activated portable device who can read human emotions.
“Detecting emotional states is becoming essential to improvements in speech recognition technology … and is a critical step on the road to true conversational AI,” said Forrest.
Telang said it was not clear whether the introduction of an emotionally intelligent voice assistant would give Spotify an edge over competing services like Apple Music.
“It looks good on paper, but it remains to be seen whether it leads to loyalty and proper returns,” Telang said.
Spotify shares certain user data with advertisers and music industry partners. While the new patent doesn’t say whether information about users’ emotions could be used in this way, Telang said it could be a problem if Spotify actually adds these capabilities.
“If the user is worried about the information being shared, they might be frightened rather than falling in love with [Spotify]”Telang said.” It’s a double-edged sword. “
Spotify did not respond to multiple requests for comment on the patent.
It might be some time before Spotify brings conversational AI to streaming music, but more improvements to its voice UI could come soon. App researcher Jane Manchung Wong recently uncovered the code for a voice activation feature – “Hey Spotify” – in the Spotify mobile application.