About DeepWave

DeepWave is a startup focusing on using AI and machine learning for audio/music analysis, retrieval, and recognition. We have been working on these areas for over 20 years, and we have won several prestigious international competitions of audio & music analysis. Our primary misson and vision is to provide brand new user experience of music and audio based on our technologies.

Music rhythm game - Lyratica

This is a element, and it's generally used – as its name implies – to spotlight a particular feature, subject, or pretty much whatever. You can customize its appearance with a number of modifiers, as well as assign it an optional transition modifier.

lyratica

Audio fingerprinting

AFP (Audio FingerPrinting) is an effective paradigm for music retrieval, which is also knowns as "query by example". Based on a given noisy recording of 8 seconds, our AFP system can identify the intended piece of music is less than a second, with an retrieval accuracy of 95%. AFP is also very power in content recognition for any media that contains audio, including video.

Audio fingerprinting

Query by Singing/Humming

QBSH (Query by Singing/Humming) is also an interesting and effective paradigms for music retrieval. Based on a singing/humming recording of 8 seconds, our QBSH system can identify the intended piece of music in 2 seconds or so, for a music database of 20K songs.

Query by Singing/Humming

Beat Tracking

BT (Beat Tracking) is a fundamental step in audio music analysis, which can detect the tempo of a music piece first, and then identify the positions of beats.

Beat Tracking

Genre/mood classification

Genre/mood classification from polyphonic audio music can be used to detect the genre (classic, jazz, country, blue, disco, etc) the music belongs to, or the mood (peace, happy, sad, anger, etc) expressed in the music.

Genre/mood classification

Singing Voice Separation

SVS (Singing Voice Separation) from polyphonic audio music is a difficult task, even for a human. Our SVS system can achieve state-of-the-art performance, and the extracted singing voices can be used for various purposes.

Singing Voice Separation

Active Noise Cancellation

ANC (Active Noise Cancellation) is a very useful technology when you want to extract your singing when enjoying mobile karaoke.

Active Noise Cancellation

Our Clients

chunghwa
esunbank
IFII
ITRI
most
tsmc

Collaborate

We are keen to customize our cutting-edge technologies for your needs. Get in touch with us!