web analytics

Google Search adds ‘Hum To Search’ feature




Google Search has recently launched the new ‘Hum to Search’ feature, allowing users to search a song by humming, singing a melody, or whistling.

It works by using the latest version of the Google app on your mobile phone. To enjoy the feature, users should go to the Google Search widget and tap the mic icon. From there, just say, “What’s this song?” or click the “Search a song” button, then start humming for 10-15 seconds. It is also accessible through the Google Assistant by saying, “Hey Google, what’s this song?” and humming the tune afterward.


 

According to Google, the feature is made possible with its machine-learning algorithm to recognize potential song matches. Users may also select the best match, explore information on the song and artist, view any accompanying music videos, listen to the song on your favorite music app, find the lyrics, read analysis, and even look for other song recordings when available.

Google also shared how its algorithm works. Each song’s melody serves as its own identity or “fingerprint.” The machine learning models can match tune, whistle, or singing to the right “fingerprint.” After humming a melody into Search, the machine learning models transform the audio into a number-based sequence representing the song’s melody. The models are also trained to identify songs based on various sources, including human singing, whistling, humming, and studio recordings. The algorithms also remove other details, like accompanying instruments and the voice’s timbre and tone, retaining only the song’s number-based sequence or the fingerprint. Furthermore, Google compares these sequences to thousands of songs globally and identifies potential matches in real-time.

This feature was made possible by the Google AI Research team’s music recognition technology. It is now available in English on iOS and in more than 20 languages on Android.

Source: Google Blog



You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *

Open

Close