ISSAI Datasets

@article{nu15071728,
AUTHOR = {Karabay, Aknur and Bolatov, Arman and Varol, Huseyin Atakan and Chan, Mei-Yen},
TITLE = {A Central Asian Food Dataset for Personalized Dietary Interventions},
JOURNAL = {Nutrients},
VOLUME = {15},
YEAR = {2023},
NUMBER = {7},
ARTICLE-NUMBER = {1728},
URL = {A Central Asian Food Dataset for Personalized Dietary Interventions},
ISSN = {2072-6643}
}

@inproceedings{yeshpanov-etal-2022-kaznerd,
title = "{K}az{NERD}: {K}azakh Named Entity Recognition Dataset",
author = "Yeshpanov, Rustem and
Khassanov, Yerbolat and
Varol, Huseyin Atakan",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "KazNERD: Kazakh Named Entity Recognition Dataset ",
pages = "417--426",
abstract = "We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward{---}but rigorous{---}rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named entity recognition were also built, with the best-performing model achieving an exact match F1-score of 97.22{\%} on the test set. The annotated dataset, guidelines, and codes used to train the models are freely available for download under the CC BY 4.0 licence from GitHub - IS2AI/KazNERD: An open-source Kazakh named entity recognition dataset (KazNERD), annotation guidelines, and baseline NER models. .",
}

@‌Article{info14020074,

AUTHOR = {Mussakhojayeva, Saida and Dauletbek, Kaisar and Yeshpanov, Rustem and Varol, Huseyin Atakan},

TITLE = {Multilingual Speech Recognition for Turkic Languages},

JOURNAL = {Information},

VOLUME = {14},

YEAR = {2023},

NUMBER = {2},

ARTICLE-NUMBER = {74},

URL = {https://www.mdpi.com/2078-2489/14/2/74 },

ISSN = {2078-2489},

ABSTRACT = {The primary aim of this study was to contribute to the development of multilingual automatic speech recognition for lower-resourced Turkic languages. Ten languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek—were considered. A total of 22 models were developed (13 monolingual and 9 multilingual). The multilingual models that were trained using joint speech data performed more robustly than the baseline monolingual models, with the best model achieving an average character and word error rate reduction of 56.7%/54.3%, respectively. The results of the experiment showed that character and word error rate reduction was more likely when multilingual models were trained with data from related Turkic languages than when they were developed using data from unrelated, non-Turkic languages, such as English and Russian. The study also presented an open-source Turkish speech corpus. The corpus contains 218.2 h of transcribed speech with 186,171 utterances and is the largest publicly available Turkish dataset of its kind. The datasets and codes used to train the models are available for download from our GitHub page.},

DOI = {10.3390/info14020074}
}

@inproceedings{
inproceedings,
author = { Mussakhojayeva, Saida and
Khassanov, Yerbolat and
Varol, Atakan},
year = {2022},
month = {09},
pages = {1367-1371},
title = {KSC2: An Industrial-Scale Open-Source Kazakh Speech Corpus}, doi = {10.21437/Interspeech.2022-421}
}

@misc{https://doi.org/10.48550/arxiv.2201.05771,
doi = {10.48550/ARXIV.2201.05771},
url = {https://arxiv.org/abs/2201.05771},
author = {Mussakhojayeva, Saida and Khassanov, Yerbolat and Varol, Huseyin Atakan},
keywords = {Audio and Speech Processing (eess.AS), Computation and Language (cs.CL), Sound (cs.SD), FOS: Electrical engineering, electronic engineering, information engineering, FOS:
Electrical engineering, electronic engineering, information engineering, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}

@Article{s21103465,
AUTHOR = {Abdrakhmanova, Madina and Kuzdeuov, Askat and Jarju, Sheikh and Khassanov, Yerbolat and Lewis, Michael and Varol, Huseyin Atakan},
TITLE = {SpeakingFaces: A Large-Scale Multimodal Dataset of Voice Commands with Visual and Thermal Video Streams},
JOURNAL = {Sensors},
VOLUME = {21},
YEAR = {2021},
NUMBER = {10},
ARTICLE-NUMBER = {3465},
URL = {https://www.mdpi.com/1424-8220/21/10/3465},
ISSN = {1424-8220},
DOI = {10.3390/s21103465}
}

@InProceedings{10.1007/978-3-030-87802-3_40,
author="Musaev, Muhammadjon
and Mussakhojayeva, Saida
and Khujayorov, Ilyos
and Khassanov, Yerbolat
and Ochilov, Mannon
and Atakan Varol, Huseyin",
editor="Karpov, Alexey and Potapova, Rodmonga",
title="USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments",
booktitle="Speech and Computer",
year="2021",
publisher="Springer International Publishing",
address="Cham",
pages="437--447",
isbn="978-3-030-87802-3"
}

@InProceedings{10.1007/978-3-030-87802-3_41,
author="Mussakhojayeva, Saida
and Khassanov, Yerbolat
and Atakan Varol, Huseyin",
editor="Karpov, Alexey
and Potapova, Rodmonga",
title="A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English",
booktitle="Speech and Computer",
year="2021",
publisher="Springer International Publishing",
address="Cham",
pages="448--459",
isbn="978-3-030-87802-3"
}

@InProceedings{10.1007/978-3-030-87802-3_41,
author="Mussakhojayeva, Saida
and Khassanov, Yerbolat
and Atakan Varol, Huseyin",
editor="Karpov, Alexey
and Potapova, Rodmonga",
title="A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English",
booktitle="Speech and Computer",
year="2021",
publisher="Springer International Publishing",
address="Cham",
pages="448--459",
isbn="978-3-030-87802-3"
}

@INPROCEEDINGS{9382623,
author={Khassanov, Yerbolat and Nurpeiissov, Mukhamet and Sarkytbayev, Azamat and Kuzdeuov, Askat and Varol, Huseyin Atakan},
booktitle={2021 IEEE/SICE International Symposium on System Integration (SII)},
title={Finer-level Sequential WiFi-based Indoor Localization},
year={2021},
volume={},
number={},
pages={163-169},
doi={10.1109/IEEECONF49454.2021.9382623}
}