To develop an Automated Real-time Transfer Model (ARM) system based on deep Nour-based neural Networks and the creation of an innovative data collection and training system for RamD (Rapid Acoustic Model Development) to achieve a superhuman performance. (Q120773): Difference between revisions

From EU Knowledge Graph
Jump to navigation Jump to search
(‎Changed an Item)
(‎Removed claim: summary (P836): The project consists of the construction of an ARM (Automatic Mic discovery) of the Voicecab in order to achieve the highest level of human performance in similar acoustic environments (super human performance) based on deep Nurone DNN (Deep Neural Network) networks. The new system for ARM VoigceLab will operate under difficult acoustic conditions, based on a very high number of training data, for different types of languages, with a high leve...)
Property / summary
The project consists of the construction of an ARM (Automatic Mic discovery) of the Voicecab in order to achieve the highest level of human performance in similar acoustic environments (super human performance) based on deep Nurone DNN (Deep Neural Network) networks. The new system for ARM VoigceLab will operate under difficult acoustic conditions, based on a very high number of training data, for different types of languages, with a high level of competitive outcome in the world. The project also aims at building a system for the rapid collection of data used for the training of acoustic models for RamD (Rapid Alert Model Development). This system will allow iteratively to carry out the research and continue the development of the speech. (English)
 
Property / summary: The project consists of the construction of an ARM (Automatic Mic discovery) of the Voicecab in order to achieve the highest level of human performance in similar acoustic environments (super human performance) based on deep Nurone DNN (Deep Neural Network) networks. The new system for ARM VoigceLab will operate under difficult acoustic conditions, based on a very high number of training data, for different types of languages, with a high level of competitive outcome in the world. The project also aims at building a system for the rapid collection of data used for the training of acoustic models for RamD (Rapid Alert Model Development). This system will allow iteratively to carry out the research and continue the development of the speech. (English) / rank
Normal rank
 

Revision as of 07:10, 21 October 2020

Project in Poland financed by DG Regio
Language Label Description Also known as
English
To develop an Automated Real-time Transfer Model (ARM) system based on deep Nour-based neural Networks and the creation of an innovative data collection and training system for RamD (Rapid Acoustic Model Development) to achieve a superhuman performance.
Project in Poland financed by DG Regio

    Statements

    country
    Poland
    0 references
    EU contribution
    4,704,949.0 zloty
    0 references
    1,129,187.76 Euro
    exchange rate to Euro
    0.24 Euro
    point in time
    13 January 2020
    0 references
    budget
    6,772,330.0 zloty
    0 references
    1,625,359.2 Euro
    exchange rate to Euro
    0.24 Euro
    point in time
    13 January 2020
    0 references
    co-financing rate
    69.47 percent
    0 references
    start time
    1 July 2016
    0 references
    end time
    30 June 2020
    0 references
    beneficiary name (string)
    VOICELAB.AI SP. Z O.O.
    0 references
    beneficiary
    Q2529518
    0 references
    summary
    Projekt polega na zbudowaniu systemu ARM (Automatyczne Rozpoznawanie Mowy) VoiceLab w celu osiągnięcia najwyższej skuteczności rozpoznawania mowy na poziomie dorównującym człowiekowi w analogicznych warunkach akustycznych (super human performance) w oparciu o głębokie sieci neuronowe DNN (Deep Neural Network). Nowy system ARM VoiceLab będzie działał w trudnych warunkach akustycznych w oparciu o bardzo dużą ilości danych treningowych, dla różnych typów języków, przy uzyskaniu poziomu wyników konkurencyjnych do najlepszych tego typu rozwiązań na świecie. Równorzędnym celem projektu jest również zbudowanie systemu do szybkiego zbierania danych wykorzystywanych do treningu modeli akustycznych RAMD (Rapid Acoustic Model Development). System ten będzie umożliwiał iteracyjnie prowadzenie badań i kontynuowanie dalszych prac rozwojowych nad rozpoznawaniem mowy. (Polish)
    0 references

    Identifiers

    Polish Kohesio ID
    RPPM.01.01.01-22-0026/16
    0 references
     
    Retrieved from "https://linkedopendata.eu/w/index.php?title=Item:Q120773&oldid=6495292"