no code implementations • SIGUL (LREC) 2022 • Phat Do, Matt Coler, Jelske Dijkstra, Esther Klabbers
ASPF was empirically confirmed to be more effective than language family as a criterion for source language selection, and also to affect the phoneme mapping’s effectiveness.
no code implementations • 21 Jun 2023 • Phat Do, Matt Coler, Jelske Dijkstra, Esther Klabbers
We compare using a PHOIBLE-based phone mapping method and using phonological features input in transfer learning for TTS in low-resource languages.
no code implementations • 1 Jun 2023 • Phat Do, Matt Coler, Jelske Dijkstra, Esther Klabbers
Results show that the G2P approach performs largely on par with using a ground-truth dictionary and the phone recognition approach, while performing generally worse, remains a viable option for LRLs less suitable for the G2P approach.
no code implementations • 30 May 2023 • Phat Do, Matt Coler, Jelske Dijkstra, Esther Klabbers
We train a MOS prediction model based on wav2vec 2. 0 using the open-access data sets BVCC and SOMOS.
no code implementations • 31 Mar 2022 • Marcel de Korte, Jaebok Kim, Aki Kunikoshi, Adaeze Adigwe, Esther Klabbers
Both sets of data are then used for student model training, which is trained to retain the naturalness and prosodic variation present in the teacher forced data, while learning the speaker identity from the augmented data.
no code implementations • 20 Aug 2020 • Marcel de Korte, Jaebok Kim, Esther Klabbers
We found that multilingual modeling can increase the naturalness of low-resource language speech, showed that multilingual models can produce speech with a naturalness comparable to monolingual multi-speaker models, and saw that the target language naturalness was affected by the strategy used to add foreign language data.
no code implementations • LREC 2020 • Jelte van Waterschoot, Iris Hendrickx, Arif Khan, Esther Klabbers, Marcel de Korte, Helmer Strik, Catia Cucchiarini, Mari{\"e}t Theune
The goal of Behaviour-based Language-Interactive Speaking Systems (BLISS) is to understand the motivations behind people{'}s happiness by conducting a personalized spoken dialogue based on a happiness model.