Speech and audio processing

The group is devoted to the speech processing technologies and its applications, with focus on the following specific areas:

  • Text to Speech Conversion: The group has its own multilingual text-to-speech conversion system, working on English, Spanish and Basque. Our AhoTTS system for Basque (aholab.ehu.es/TTS) is the only one fully developed at the Basque Country and it is freely available. It is also able to generate emotional synthetic speech.
  • Speech Synthesis: A big research effort is devoted to the synthetic speech generation algorithms and technologies, to be incorporated into the AhoTTS for its evaluation. Virtually all state of the art speech generation technologies have been developed and evaluated through the last 15 years.
  • Music and singing: We have explored the applications of speech synthesis in the field, developing singing synthesis and a signal processing tool for music teaching.
  • Prosody modelling: Prosody models and prosody generation techniques have been developed specifically for the Basque language. Special focus was on prosody analysis and conversion techniques applied to the generation of emotional speech.
  • Speech recognition: The group has developed several public speech databases for the development and test of speech recognition systems for Basque, all of them available through ELRA. A reduced vocabulary isolated and connected word recognition system for Basque has also been developed, and a continuous speech recognizer is now being developed.
  • Speaker recognition and speaker diarisation: We have participated in the past in several national projects involving speaker recognition. Presently this is a very active research area, with 2 live national projects and several international collaborations (see publications 2010). The recognition of the speaker emotions has also been a very active and productive research field during the last 4 years
  • Machine listening: We have experience in extracting information out of audio and voice signals, being the most important achievement the detection of noises inside vehicles.
Main Researcher: 
Researchers: 
Eva Navas
Jon Sanchez
Xabier Sarasola
Ibon Saratxaga

see more

tts_tabs

Demos

Projects

Publications

Inge Salomons, Eder del Blanco, Eva Navas, Inma Hernáez 

Electrode Setup for Electromyography-Based Silent Speech Interfaces: A Pilot Study (2025)

del Blanco, E., Salomons, I., García, V., Navas, E., Hernáez, I. 

Comparative Analysis of Mono-speaker and Multi-speaker Models for EMG-to-Speech Conversion (2024)

Salomons, I., Hernáez, I., Navas, E., Wieling, M. 

Analyzing Speech Muscle Activity Using Generalized Additive Modeling (2024)

de Zuazo, X., Verbeni, V., Ku, L.-C., Arrieta, E., Barrena, A., Klimovich-Gray, A., Saratxaga, I., Navas, E., Agirre, E., Molinaro, N. 

#neural2speech: Decoding Speech and Language from the Human Brain (2024)

Külebi, B., Hernáez, I., Fernández Rei, E., Montoyo, A., Solito, S., Armentano-Oller, C., Hernando, J., Navas, E., Magariños, C., Vladu, A., Saratxaga, I., Sánchez, J., García Romillo, V., Herranz, A., Souganidis, C., García, N., Moscoso Sánchez, A., Regueira, X.L., Dubert, F., Gutiérrez, Y. 

Speech Technologies in the ILENIA Project: Generating Resources to Develop Voice Applications in the Official Languages of Spain (2024)

Herranz, A., García-Sebastián, A., Souganidis, C., García-Romillo, V., Bellanco, A., Navas, E., Hernáez-Rioja, I., Saratxaga, I. 

HiTZ-AhoLab ASR System for the Albayzin Bilingual Basque-Spanish Speech to Text Challenge (2024)

Souganidis, C., Meseguer, G., Herranz, A., Hernáez Rioja, I., Navas, E., Saratxaga, I. 

HiTZ-Aholab Speaker Diarization System for Albayzin Evaluations of IberSPEECH 2024 (2024)

Messaoudi, A., Solito, S., Costa, F., Hernández Mena, C.D., Casals-Salvador, M., Takanori Sanchez Shiromizu, L., Cortada Garcia, M., Armentano-Oller, C., Moscoso Sánchez, A., Magariños, C., González Corbelle, J., Herranz, A., Souganidis, C., Hernáez Rioja, I., Saratxaga, I., Navas, E. 

ILENIA_VOZ ASR System Fusion for Albayzin 2024 Speech to Text Challenge (2024)

Eneko Agirre, Itziar Aldabe, Xabier Arregi, Mikel Artetxe, Unai Atutxa, Ekhi Azurmendi, Iker de la Iglesia, Julen Etxaniz, Víctor García Romillo, Inma Hernáez Rioja, Asier Herranz, Mikel Iruskieta, Oier López de Lacalle, Eva Navas, Paula Ontalvilla, Aitor Ormazabal, Naiara Pérez, German Rigau, Oscar Sainz, Jon Sánchez, Ibon Saratxaga, Aitor Soroa, Christoforos Souganidis, Jon Vadillo, Aimar Zabala. 

IKER-GAITU: Research on Language Technology for Basque and Other Low-Resource Languages. (2024)

Eneko Agirre, Olatz Arbelaitz, Olatz Arregi, Gorka Azkune, Arantza Casillas, Inma Hernáez, Mikel Iruskieta, Elena Lazkano, Eva Navas, German Rigau, Roberto Santana, Aitor Soroa, Rabih Zbib 

ENIA Chair in Artificial Intelligence and Language Technology (2024)

All HiTZ publications