Maxim Tkachenko
About
Detail
Co-Founder
Portugal
Résumé
Jobs
verified_user
0% verified
Co-FounderHumanSignalJan 2019 - Current (7 years 7 months)- Senior Software EngineerASM SolutionsOct 2015 - May 2019 (3 years 8 months)Speech recognition
- Software EngineerSTEL Computer SystemsMay 2011 - Oct 2015 (4 years 6 months)Machine learning algorithms engineering (speech recognition), high-performance computing development.
- LScientific adviser, teacherLITMar 2011 - May 2012 (1 year 3 months)
- CSound programmer and product ownerCasual UndergroundJan 2010 - Dec 2012 (3 years)Loopseque, Movbeats
- Photo & Video & DesignfreelanceJan 2008 - Current (18 years 7 months)Advertisement video, music video, short films
Education
verified_user
0% verified
- Master's degree, Computer ScienceLomonosov Moscow State University MSUJan 2005 - Jan 2010 (5 years 1 month)
- LLit 1533LITJan 2003 - Jan 2005 (2 years 1 month)
Projects (professional or personal)
verified_user
0% verified
- LLabel StudioJan 2019 - Current (7 years 7 months)Data Labeling Software for Machine Learning
- TTestariumJun 2013 - Mar 2019 (5 years 10 months)Testarium is a research tool to perform experiments and store results as in the repository (git or mercurial). It implements scientific template of experiments and uses numpy, colorama, flask, d3, jquery-ui and angular to provide powerful shell and beautiful presentation of your experimental data and scores. It can be helpful for science researchers and their bosses to monitor the work progress and to optimize parameters.
- WWORMTUNE: Intelligent Music PlatformMar 2012 - Mar 2013 (1 year 1 month)Data mining techniques for automatical indexing and retrieval of musical tracks
- OOnline speech processing serviceMay 2011 - Jan 2019 (7 years 9 months)- speech-to-text automatic transcription - speaker identification & verification - language recognition - spoken dialogue system
- LLoopsequeJun 2010 - Jun 2012 (2 years 1 month)Loopseque is an incredibly simple app for creating music. With Loopseque making music is like playing a game. You can create beats, switch fast between patterns and arrange compositions. It’s easy and fun.
Publications
verified_user
0% verified
- ASpeech Enhancement for Speaker Recognition Using Deep Recurrent Neural NetworksAug
- SApplication of l_1 Estimation of Gaussian Mixture Model Parameters for Language IdentificationSpeech and Computer Lecture Notes in Computer Science Volume pp
- JLanguage Identification Using Time Delay Neural Network D-Vector on Short UtterancesJan
- Lightweight embeddings for speaker verificationSEP