Aholab is the short name of the Signal Processing Laboratory of the University of the Basque Country (UPV/EHU). The laboratory is located in Bilbao. We are a university research team and focus our research in the areas of Text to Speech Conversion, Speech and Speaker Recognition, and Speech Processing in general. Since 2005 we are a recognized research group of the Basque Research Network. The laboratory is part of the Basque Center for Language Technology (HiTZ) and the Department of Communications Engineering of the Faculty of Engineering of Bilbao (ETSI).
Tuesday, June 12th
17:30
ADELA – ARABA
During the course of certain diseases, such as ALS, the ability to speak fluently can be lost. However, this should not mean losing communication with our surroundings: family members, caregivers, and others. This can be made possible through electronic devices that allow us to produce messages using a synthetic voice. In this talk, we will tell about the AhomyTTS project, which makes it possible for that synthetic voice to resemble the one we have now.
Our activity on the social network Bluesky begins.
From now on, you can find us at https://bsky.app/profile/aholab.bsky.social.
Contract duration: 16 months
Available positions: 0 (both have been assigned)
Job Description: We are looking for two people from the IT or telecommunications field, with a passion for artificial intelligence and neural networks. In this exciting project, you will work on developing and refining voice creation and recognition systems.
Responsibilities:
Requirements:
Benefits:
If you are interested in joining our team and contributing to the future of speech recognition technology, we look forward to your application! Tell us!
More information here and here.
From the Aholab Group and the HiTZ center we present to the public the new speech recognition system in Basque. This technological advance has the potential to transform the interaction between people and technology, especially in the field of the Basque language.
The system has been trained with 548 hours of Basque voices from different public sources (Mozilla Common Voice 16.1, Basque Parliament, OpenSLR), which allows it to accurately recognize the words and phrases spoken by users, reaching quality levels of WER less than 5%.
Two different models have been created based on NVIDIA pre-trained models. One of them using a language model with more classic techniques, and the other using more emerging technologies such as transducers. The training of the models was carried out on the Hyperion system from the DIPC servers.
The system can potentially be integrated into virtual assistants to perform tasks such as sending messages, searching for information or setting reminders. It could also enable the automation of responses to telephone calls, improving efficiency and customer service. And it will facilitate the transcription of audio recordings in Basque.
A demo of the speech recognition system in Basque is available at this link and the models are available at Gaitu-Data. The team invites the community to use it and provide feedback to continue improving the technology. We hope that it will be a valuable tool for the Basque community and contribute to the strengthening of our language.
Aholab is member of:
