Name: Technologies for automatic annotation of audio data and for the creation of automatic speech recognition interfaces (TADARAV)
General Objective
The project "Technologies for automatic annotation of audio data and for the creation of automatic speech recognition interfaces" (TADARAV) has as main purpose the design, implementation and validation of automated annotation technologies for speech units. This project primarily aims at developing a set of advanced technologies for generating transcriptions correctly aligned with the voice signal from the corpus collected in the COBILIRO component project. As a side effect, the project aims to increase the accuracy of SpeeD's current automatic speech recognition system (RAV) by retraining its acoustic model based on the entire collected speech corpus and using more powerful language models generated in the TEPROLIN component project.
Motivation
At present, over 7,000 different languages or dialects are spoken in the various countries of the world. In this context, if the automated speech recognition systems (RAV) for international languages are very performant, for a large part of the existing languages the task is quite difficult. The reason is very simple: there are not enough acoustic and linguistic resources annotated for these languages. Hence the name of poor-endowed languages. For the development of a RAV system, huge amounts of annotated data are needed to train acoustic, linguistic and phonetic models.
The creation of performing RAV systems for poor-endowed languages through the normal development stages (resource acquisition, modeling, algorithm adaptation) is impossible in the near future. This motivates the effort to identify new automatic methods of annotating acoustic and linguistic data (existing abundantly but not yet annotated) in order to obtain RAV systems for poor-endowed languages.
Thus, the specific objectives of the TADARAV project are:
Design, implementation and validation of various methods of filtering and aligning approximate transcripts with speech signal
Performing an analysis of various ways of calculating RAV reliability scores and then designing, implementing and validating various methods for generating confidence scores well correlated with the correct transcription
Design, implement, and validate an automated speech annotation method using multiple complementary RAV systems
Working Plan
The project is structured in 3 stage, corresponding to the reporting stages. Each stage is based on the results of the previous stages or studies in the project and on the results obtained in the parallel projects within the complex project, as follows:
Stage 1: Conducting state-of-the-art studies for automatic annotation of speech corpuses by going through specialized literature
Stage 2: Design and implementation of basic solutions for automatic annotation of speech corpuses using existing RAV systems
Stage 3: Implementation of prototypes / demonstration for automatic annotation of speech corpuses using existing RAV systems
Expected Results
The expected results in each phase of the project (some also based on the results obtained in the parallel projects within the complex project) are as follows:
Stage 1:
State-of-the-art study - Methods for using complementary RAV systems to automatically generate annotations
State-of-the-art study - Methods for aligning approximate transcripts with speech signal
State-of-the-art study - Methods for generating RAV confidence scores
Basic solution for automatic annotation of speech signal using complementary RAV systems
Stage 2:
Basic filter solution and alignment of approximate transcripts with speech signal
Basic solution for generating RAV confidence scores
Enhanced automatic speech annotation solution using complementary RAV systems
Stage 3:
Analysis report on the impact of complementary RAV use for generating annotations in the context of RAV systems improvement
Improved solution for generating reliable RAV scores
RAV system
Analysis report of the impact of using approximate transcripts for RAV retrainings
Analysis report of the impact of using the confidence scores for filtering RAV transcripts for retraining RAV systems
CONSORTIUM
Research Institute for Artificial Intelligence "Mihai Drăgănescu", Bucharest
Technical University Of Cluj-Napoca
University Politehnica Of Bucharest
"Alexandru Ioan Cuza" University Of Iași
Team
University POLITEHNICA of Bucharest
Prof. Corneliu Burileanu
Prof. Dragoș Burileanu
Assoc. Prof. Horia Cucu
PhD Dan Oneață
PhD student Gheorghe Pop
PhD student Lucian Georgescu
Eng. Cristian Manolache
Institute for Research for Artificial Intelligence "Mihai Drăgănescu", Bucharest
Acad. Dan Tufiș
PhD Verginica Mititelu
PhD Radu Ion
PhD Elena Irimia
Technical University of Cluj-Napoca
Prof. Mircea Giurgiu
PhD Adriana Stan
„Alexandru Ioan Cuza” University of Iași
Prof. Dan Cristea
PhD Anca Bibiri
PhD Ionuț Pistol
PhD Diana Trandabăț
Scientific Reports
State-of-the-art study - Methods for using complementary RAV systems to automatically generate annotations
State-of-the-art study - Methods for aligning approximate transcripts with speech signal
State-of-the-art study - Methods for generating RAV confidence scores
Analysis report on the impact of complementary RAV use for generating annotations in the context of RAV systems improvement
Analysis report of the impact of using approximate transcripts for RAV retrainings
Analysis report of the impact of using the confidence scores for filtering RAV transcripts for retraining RAV systems
Romanian Academy Research Institute for Artificial Intelligence “Mihai Drăgănescu” (ICIA) was set up in 1994 as a centre of competence and active dissemination of knowledge in the domain of Artificial Intelligence. ICIA has a core of permanent research positions and a small number of consultant researchers. Besides them, a variable number of contract-based positions, especially students, participate in the R&D activities of ICIA. Every year, since its foundation, ICIA was evaluated as an excellency institution by the Romanian Academy. In 2001 ICIA won the competition for Centres of Excellency (in Information Science and Technology) organized by the Ministry of Education and Science. In 2002 it was rated the best research institute of the Romanian Academy (from 60 institutes and centres). In 2002 ICIA was granted the right to organize doctoral studies in the Romanian Academy system. In 2008 ICIA was accredited as a research institution and as a research and development, member of the research and development system of national interest, in conformity with HG no. 551/2007.
In 1947, following a memorandum addressed to the Ministry of National Education on the establishment of a Polytechnic in Cluj with three faculties: Constructions, Electromechanics and Silviculture, through the provisions of the Law on Education Reform of August 1948, the Institute of Mechanics from Cluj was established, having a faculty with two sections: Thermotechnics and Work Machines. The increase in the need for technical staff made the Institute of Mechanics in 1953 transform into the Polytechnic Institute of Cluj.
After the revolution in 1989, the Romanian higher education returned to the Romanian tradition correlated with the Western system. Starting with 1992, the Polytechnic Institute changed its name to the Technical University of Cluj-Napoca, and from the three faculties that existed at that moment, through restructuring, seven faculties were created: Automation and Computers, Electronics, Telecommunications and Information Technology, Engineering Electrical Engineering, Construction, Machine Building, Mechanics, Materials Science and Engineering (becoming in 2011 Engineering Materials and Environment), as well as the Technical, Economic and Administrative University College. In 1998, the structure of the Technical University of Cluj-Napoca complemented with the Faculty of Architecture and Urbanism and in 2007, with the Faculty of Installations.
Since 2012, the Technical University of Cluj-Napoca has thirteen faculties following the merger with the North University of Baia-Mare, which became the North University Center in Baia Mare, comprising the Faculty of Engineering, the Faculty of Letters, the Faculty of Mineral Resources and Environment and the Faculty of Sciences. At present, the Technical University of Cluj-Napoca prepares specialists through bachelor, master, doctorate and postgraduate studies, with the number of students exceeding 20,000. The fundamental, or applicative scientific research is an essential preoccupation of the teaching staff and researchers at UTCN. The scientific potential of the University has enabled it to organize or be involved in the organization of large-scale scientific events with a large participation of Romanian and foreign specialists.
University POLITEHNICA of Bucharest is the oldest and most prestigious engineer school in Romania. Its traditions are related to the establishment, in 1818, by Gheorghe Lazar, of the first higher technical school with teaching in Romanian language, in the Saint Sava Monastery in Bucharest. In 1832, it was reorganized into the Saint Sava College.
.
On October 1, 1864, the School of Bridges and Roads, Mine and Architecture was established, and on October 30, 1867, it became the School of Bridges, Roads and Mine, with studies duration of 5 years. Under the leadership of Gheorghe Duca, on April 1, 1881, the institution acquires a new structure, under the name of "The National School of Bridges and Roads"; on June 10, 1920, the Politehnica School of Bucharest was founded, with four sections: Electromechanics, Construction, Mining and Metallurgy, Industrial Section.
From November 1920 the name changes to POLITEHNICA of Bucharest.
On August 3, 1948, the Polytechnic Institute of Bucharest was founded, which initially included 4 faculties and in which, since 1950, most of the today faculties have appeared. Based on the resolution of the Senate of November 1992, the Polytechnic Institute of Bucharest became University POLITEHNICA of Bucharest.
At University POLITEHNICA of Bucharest, people are trained without whom the society, as we know it today, could not work - the engineers. We are a nation with inherited technical abilities, with native engineering inclination, and many times Romanian engineers have added their name to the pantheon of world science.
A history of the University of Iaşi takes us through the lessons of the history book of the Romanians from the 16th century. If, in general, the existence of a university is linked to the historical context, in Romania, the University of Iasi has often played a role as a creative historian. In the 17th century, for example, the university was a shelter of Byzantine culture; later it was one of the most important factors in spreading the Romanian language and indigenous culture; after its establishment as the first modern higher education institution of Romania, the university provided the state with the most important thinkers and actors in the public life so that, during communism, the humanist spirit could be kept alive.
