%Aigaion2 BibTeX export from Idiap Publications
%Monday 04 March 2024 02:58:24 PM

         author = {Chen, Haolin and He, Mutian and Coppieters de Gibson, Louise and Garner, Philip N.},
       projects = {Idiap, NAST},
          month = aug,
          title = {The Idiap Speech Synthesis System for the Blizzard Challenge 2023},
      booktitle = {Proc. 18th Blizzard Challenge Workshop},
           year = {2023},
            doi = {10.21437/Blizzard.2023-13},
       abstract = {This paper presents the text-to-speech (TTS) system submitted by Idiap Research Institute to the Blizzard Challenge 2023. Our system follows the conventional pipeline of text analysis, acoustic modeling (AM) and vocoding. For text analysis, open-source pretrained part-of-speech (POS) taggers and lemmatizers are utilized to provide more accurate grapheme-to-phoneme (G2P) conversion on top of the eSpeak backend. The rest of the system incorporates a fully diffusion-based approach which comprises a diffusion transformer-based acoustic model and FastDiff as the vocoder, both of which are trained only on the provided data to ensure high-quality synthesis. Our entry provides a baseline for the cascading diffusion AM-vocoder architecture since no extra design is adopted to enhance the naturalness of speech. Evaluation results have demonstrated high synthesis quality of our system and the effectiveness of the proposed phonemization pipeline.},
            pdf = {https://publications.idiap.ch/attachments/papers/2023/Chen_BLIZZARD2023_2023.pdf}