ASR, TTS, voice biometry, VR
The main area of Techmo’s activity consists of implementing business solutions in the scope of speech technology and computer processing of natural language. We have been operating on the market since 2013.
ASR (Automatic Speech Recognition) is a technology that has been evolving for several decades — primarily for the English language. Techmo ASR is a system for the automatic recognition of Polish speech. It is used as a voice interface for applications or call steering. It can be used as an acoustic search engine or for creating voice notes. It is based on the latest achievements in technology (deep learning), and it is fully adaptable to other languages.
Techmo offers a high-quality TTS (Text-to-Speech) tool for the synthesis of Polish speech. TRYBUN is an efficient and precise software for converting text to speech. The applied technologies guarantee high accuracy, naturalness and efficiency of the synthesis. The system can be easily adapted to a full range of natural, new, individually selected voices.
SEZAM is a solution allowing the identification of a speaker, combined with the possibility of verification and authorisation. It increases the level, comfort and quality of user experience. The system’s operation is independent of intonation or temporary change of the tone of voice resulting from external factors (such as hoarseness, ambient temperature, etc.). Any voice sample of at least 1600 milliseconds in length will be sufficient. For recordings over 5 seconds, the system enables performing various tasks related to the mapping of speakers.
SoundToolKit is an innovative tool developed by Techmo that allows for realistic simulation of the behaviour of any sound in a 3D environment. Such elements as the layout of the building, materials, size, motion of the sound source or position of the listener are taken into account in the simulation. The simulation is executed on an ongoing basis, taking into consideration the surrounding conditions that change dynamically. The system was designed for the video game market as a tool that simplifies and speeds up the work of developers.
Techmo was established as a spin-off in cooperation with the AGH University of Science and Technology in Krakow. Our team is primarily composed of scientists and IT specialists who combine research-related passions with its practical use in various areas of life. We specialise in sound and speech analysis but we are also passionate about the latest technologies used in computer games. Despite the academic outlook, we understand the needs of an innovative business very well. Change is what makes the world go round. In order for a business to catch up to the changing reality, it has to
use solutions that exceed its era and Techmo delivers such products. Techmo cooperates with a number of institutions and NGOs as a participant of a public debate concerning new challenges related to speech and its digitalization. These entities include: Polish Ministry of National Defence, Kosciuszko Institute, Polish Ministry of Digital Affairs, Hokkaido University, University of Kent, Pacific Voice and Speech Foundation, Siódmy Zmysł Foundation.
Sign the Declaration
The document is the work of the community of Polish startups - young and experienced entrepreneurs, investors, technology park representatives and local startup activists - united to speak with a single voice.
- Bartłomiej Michałowskihas just joined
- Jan Nowakthanks for sign off
- Aleksander Olenderis with us
- Patrycja Wójcikwelcome on board
- Aniela Matusiakjust signed the Manifesto
- Michał Lutostańskijoined us
- Juliana Panaszukhas just joined
- Maciej Dąbrowskithanks for sign off
4586 people have signed the Declaration