| The name of the base system (platform): | Cloud platform of Mail.ru for business |
| Developers: | Mail.ru Group |
| Technology: | PaaS - Platform As A Service - the Business platform as service, cybersecurity - Biometric identification, Speech technologies |
Mail.ru Sounds is service of audioanalytics. A cloud technology of processing and synthesis of sounds from Mail.Ru Cloud Solutions. Detects and analyzes any sounds or their combination in an audio stream. API for integration of recognition of sounds and the speech based on machine learning.
2020: Possibilities of Mail.ru Sounds
Among opportunities there is Mail.ru Sounds for March, 2020:
- Will recognize separate sounds and their combinations in an audio stream
- Foresees a situation on the basis of a combination of sounds
- Distinguishes the volume, tonality, intensity of sounding
- Notifies that a certain sound is detected
- Learns and separates sounds even in big noise
- Works with the speech: will recognize voices and will transform to the text
2018
On October 22, 2018 the Mail.Ru Group company reported that it started a product within the Mail Cloud Solutions platform — service of audioanalytics Sounds. According to the company, service which cornerstone machine learning technologies are allows to automate and simplify many ordinary processes.
The sensing technology of sounds can be used in a set of scenarios: recognition of separate sounds in an audio stream (shouts, shots, steps, sounds of the broken glass, crying), cleaning of audio recordings of noise, identification of people on voices, increase in clearness of a voice of the announcer, identification of malfunctions in operation of mechanisms. The service of audioanalytics Sounds working based on neural networks allows to solve problems in spheres of security, retail, media, telecommunications, etc.
Using audioanalytics it is possible to process both archive files, and online flows. In a number of situations the technology is applied as an alternative to video surveillance: the technology will recognize sounds in complete darkness, and microphones cost much cheaper than cameras and do not require special conditions for placement and service.
Neural networks of "computer hearing" are trained at own data sets of Mail.Ru Group and work at server capacities of the company that guarantees the high speed and uninterrupted operation of service.
 | Mail.Ru Group entered the market of computer vision, having started the Vision project. We were convinced that the solution is demanded therefore went further and complemented sight with hearing. The technology will allow to develop efficiency of 'offer' in general. For example, non-standard noise or rustle on an observed object should cause suspicion if it is about security functions. This perspective direction which for October, 2018 actively develops. |  |
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |