The Institute of Smart Systems and Artificial Intelligence (ISSAI) made a mark at the 24th INTERSPEECH Conference, held from August 20th to 24th in the vibrant city of Dublin, Ireland. INTERSPEECH is the world’s largest and most comprehensive event for the speech processing and application community.
At this prestigious and top conference, ISSAI’s Technical Writer, Rustem Yeshpanov, presented a paper titled “Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration”. Authored by Rustem Yeshpanov, Saida Mussakhojayeva, and Yerbolat Khassanov, the paper introduced a multilingual end-to-end text-to-speech system designed for ten Turkic languages. This system, encompassing Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkmen, Turkish, Uyghur, and Uzbek, leveraged Kazakh as the only source language for development. The approach adopted by the researchers garnered significant attention and received a warm reception from the speech processing community.
This year’s INTERSPEECH conference witnessed an impressive participation of 1,976 individuals from 63 different countries. ISSAI proudly represented Kazakhstan as the sole organization from the country, showcasing its commitment to advancing research in the field. The conference featured 1,097 presentations, 98 technical sessions, 9 special sessions, 9 survey talks, 8 tutorials, 3 keynote speeches, and 1 enlightening keynote discussion.
Moreover, the INTERSPEECH conference extended beyond the main event with several satellite workshops and tutorials. ISSAI participated in the 2nd Annual Meeting of the Special Interest Group on Under-resourced Languages, further demonstrating its dedication to promoting research for Turkic languages, most of which are generally considered under-resourced.
As the 24th INTERSPEECH Conference drew to a close, anticipation mounted for the next edition. The 25th INTERSPEECH Conference is slated to take place in Jerusalem, Israel, promising another exciting opportunity for researchers and innovators to converge and shape the future of speech processing technology.