TY - GEN
T1 - TatarTTS
T2 - 6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024
AU - Orel, Daniil
AU - Kuzdeuov, Askat
AU - Gilmullin, Rinat
AU - Khakimov, Bulat
AU - Varol, Huseyin Atakan
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - This paper introduces an open-source dataset for speech synthesis in the Tatar language. The dataset comprises approximately 70 hours of transcribed audio recordings, featuring two professional speakers (one male and one female). Notably, it is the first large-scale dataset of its kind that is publicly available, aimed at promoting Tatar text-to-speech (TTS) applications in both academic and industrial contexts. The paper describes the procedures for developing the dataset, discusses the challenges faced, and outlines important future directions. To demonstrate the reliability of the dataset, baseline end-to-end TTS models were built and evaluated using the subjective mean opinion score (MOS) measure. The dataset, training recipe, and pretrained TTS models are publicly available.
AB - This paper introduces an open-source dataset for speech synthesis in the Tatar language. The dataset comprises approximately 70 hours of transcribed audio recordings, featuring two professional speakers (one male and one female). Notably, it is the first large-scale dataset of its kind that is publicly available, aimed at promoting Tatar text-to-speech (TTS) applications in both academic and industrial contexts. The paper describes the procedures for developing the dataset, discusses the challenges faced, and outlines important future directions. To demonstrate the reliability of the dataset, baseline end-to-end TTS models were built and evaluated using the subjective mean opinion score (MOS) measure. The dataset, training recipe, and pretrained TTS models are publicly available.
KW - low-resource languages
KW - speech synthesis
KW - Text- to-speech
KW - Turkic languages
UR - http://www.scopus.com/inward/record.url?scp=85189929366&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85189929366&partnerID=8YFLogxK
U2 - 10.1109/ICAIIC60209.2024.10463261
DO - 10.1109/ICAIIC60209.2024.10463261
M3 - Conference contribution
AN - SCOPUS:85189929366
T3 - 6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024
SP - 717
EP - 721
BT - 6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 February 2024 through 22 February 2024
ER -