Speech Processing

Tilde has worked on spoken language processing since the late 1990s.

Tilde’s researchers has developed a world's first Latvian automatic speech recognition and text-to speech systems. The research result -  Latvian automatic speech recognition service -is freely available as a web service.  Latvian automatic speech recognition and text-to speech systems are also integrated in Tilde's products. 

Speech Technology research

Driving Force for Development of Speech Technology for Baltic Languages

Tilde continues research on speech recognition by adapting developed technologies for new languages (e.g. Lithuanian) and for specific domains (e.g. medicine, public debates, etc.). The special attention is paid to data sparseness problem that is typical for morphologically rich languages and to novel methods for data acquisition from the web. New application domain - dictation – is also among active research topics. Finally, methods for speech recognition from low quality data are actively researched.

Where it concerns speech synthesis, Tilde’s experience cover different methods, including unit selection, parametric synthesis and recently parametric synthesis with neural networks. 

.

PROJECTS

Ongoing projects

Odine project

Open Data Incubator for Europe

ODINE aims to support the next generation of digital businesses and support them to fast-track the development of their products. 

Read more
QT 21 project

Quality Translation 21

Project aims to develop substantially improved statistical and machine-learning based translation models for challenging languages and resource scenarios.

Read more
european language resource coordination

European Language Resource Coordination

The objective of the project to identify and gather language and translation data relevant to public administration across all 30 European countries.

Read more

Publications

2023

Marcin Skowron, Gerhard Backfried, Eva Navas, Aivars Bērziņš (Tilde), Joachim Van den Bogaert, Franciska de Jong, Andrea DeMarco, Inma Hernáez, Marek Kováč, Peter Polák, Johan Rohdin, Michael Rosner, Jon Sanchez, Ibon Saratxaga and Petr Schwarz.2023. Deep Dive Speech Technology. European Language Equality, Springer, 289–312.

2022

Ian Roberts, Penny Labropoulou, Dimitris Galanis, Rémi Calizzano, Athanasia Kolovou, Dimitris Gkoumas, Andis Lagzdiņš (Tilde), and Stelios Piperidis. 2022. Using the European Language Grid as a ConsumerEuropean Language Grid. A Language Technology Platform for Multilingual Europe, Springer, 37-66. 

Ian Roberts, Andres Garcia Silva, Cristian Berrìo Aroca, Jose Manuel Gómez-Pérez, Miroslav Jánošík, Dimitris Galanis, Rémi Calizzano, Andis Lagzdiņš (Tilde), Milan Straka, and Ulrich Germann. 2022. Language Technology Tools and Services.  European Language Grid. A Language Technology Platform for Multilingual Europe, Springer, 131-149.