Listado de socios
Techmo implements business solutions in the field of speech technology, natural language processing and sound virtualization by using:
- speech recognition – changes human speech into text. Operates both by recognizing natural speech and closed SRGR sets,
- speech analysis – seeks out keywords and phrases in any voice database. Works both online – in real time – and offline – recording analysis,
- speech synthesis – changes any text into fluent speech. As an additional option, one can create a dedicated brand voice,
- sound virtualization – simulation of sound physics in 3D environment. Analyses materials used in scene construction, space architecture, reflections, sound transmission, muting, etc.
These solutions may be used in such areas as:
- Process Automation – preliminary client service, soft asset recovery, survey of huge responder datasets, automatic phone reservation or confirmation,
- IoT – security of intermachine communication, user interface for intelligent buildings
- Telemedicine – diagnostics based on voice samples by recognition and assessment of the risk of an occurence of a medical condition based on a voice recording,
- Security – quality assurence by analysis of quantity and quality of large datasets, finding key words and whole sentences, looking for context and regularities,
- Game development – creation of natural sounds in a game environment, acceleration and automation of sound engineers and audio developers work in VR/AR environments and games.