<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">kaz29</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Казахстанско-Британского технического университета</journal-title><trans-title-group xml:lang="en"><trans-title>Herald of the Kazakh-British Technical University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1998-6688</issn><issn pub-type="epub">2959-8109</issn><publisher><publisher-name>Казахстанско-Британский Технический Университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.55452/1998-6688-2025-22-4-23-30</article-id><article-id custom-type="elpub" pub-id-type="custom">kaz29-2276</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ НАУКИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>ПРИМЕНЕНИЕ НЕАВТОРЕГРЕССИОННОГО ДЕКОДИРОВАНИЯ ДЛЯ РАСПОЗНАВАНИЯ КАЗАХСКОЙ РЕЧИ</article-title><trans-title-group xml:lang="en"><trans-title>APPLICATION OF NON-AUTOREGRESSIVE DECODING FOR KAZAKH SPEECH RECOGNITION</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4975-6493</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Оралбекова</surname><given-names>Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Oralbekova</surname><given-names>D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>PhD, старший научный сотрудник</p><p>г. Алматы</p></bio><bio xml:lang="en"><p>PhD, Senior Researcher</p><p>Almaty</p></bio><email xlink:type="simple">dinaoral@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8318-3794</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Мамырбаев</surname><given-names>О.</given-names></name><name name-style="western" xml:lang="en"><surname>Mamyrbayev</surname><given-names>O.</given-names></name></name-alternatives><bio xml:lang="ru"><p>PhD, профессор, главный научный сотрудник</p><p>г. Алматы</p></bio><bio xml:lang="en"><p>PhD, Professor, Chief Researcher</p><p>Almaty</p></bio><email xlink:type="simple">morkenj@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2013-1513</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Еримбетова</surname><given-names>А.</given-names></name><name name-style="western" xml:lang="en"><surname>Yerimbetova</surname><given-names>A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>PhD, к.т.н., ассоц. профессор</p><p>г. Алматы</p></bio><bio xml:lang="en"><p>PhD, Cand.Tech.Sc., Associate Professor</p><p>Almaty</p></bio><email xlink:type="simple">aigerian8888@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-3984-2718</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Бекарыстанқызы</surname><given-names>А.</given-names></name><name name-style="western" xml:lang="en"><surname>Bekarystankyzy</surname><given-names>A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>PhD, старший научный сотрудник</p><p>г. Алматы</p></bio><bio xml:lang="en"><p>PhD, Senior Researcher</p><p>Almaty</p></bio><email xlink:type="simple">akbayan.b@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1470-3706</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тұрдалыұлы</surname><given-names>М.</given-names></name><name name-style="western" xml:lang="en"><surname>Turdalyuly</surname><given-names>M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>PhD, старший научный сотрудник</p><p>г. Алматы</p></bio><bio xml:lang="en"><p>PhD, Senior Researcher</p><p>Almaty</p></bio><email xlink:type="simple">m.turdalyuly@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Институт информационных и вычислительных технологий КН МНВО РК<country>Казахстан</country></aff><aff xml:lang="en">Institute of Information and Computational technology<country>Kazakhstan</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>23</day><month>12</month><year>2025</year></pub-date><volume>22</volume><issue>4</issue><fpage>23</fpage><lpage>30</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Оралбекова Д., Мамырбаев О., Еримбетова А., Бекарыстанқызы А., Тұрдалыұлы М., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Оралбекова Д., Мамырбаев О., Еримбетова А., Бекарыстанқызы А., Тұрдалыұлы М.</copyright-holder><copyright-holder xml:lang="en">Oralbekova D., Mamyrbayev O., Yerimbetova A., Bekarystankyzy A., Turdalyuly M.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://vestnik.kbtu.edu.kz/jour/article/view/2276">https://vestnik.kbtu.edu.kz/jour/article/view/2276</self-uri><abstract><p>В области распознавания речи интегральные модели постепенно вытесняют традиционные и гибридные подходы. Основным их принципом является автогрессионное декодирование, при котором выходная последовательность формируется слева направо. Однако до сих пор не было доказано, что этот метод дает наилучшие результаты при преобразовании речи в текст. Кроме того, интегральные модели полагаются только на предыдущий контекст, что затрудняет обработку нечетких или искаженных звуков. В связи с этим был предложен метод Insertion, который не использует автогрессионное декодирование и генерирует выходные данные в произвольном порядке. В данной работе рассматривается модель распознавания казахской речи, обученная на основе метода Insertion и коннекционной временной классификации (CTC). Проведенные эксперименты показали, что этот метод позволяет повысить точность распознавания. В отличие от автогрессионных моделей, метод Insertion предоставляет большую гибкость в обработке последовательностей, поскольку не требует строгого порядка формирования выходных данных. Это снижает задержки при декодировании и делает модель более устойчивой к нечетко произнесенным словам. Кроме того, сочетание метода Insertion с CTC позволяет улучшить соответствие аудиоданных и текстовой транскрипции. Это особенно важно для агглютинативных языков, таких как казахский. По результатам экспериментов точность распознавания предложенной модели достигла 10,2%, что делает ее конкурентоспособной на сегодняшний день.</p></abstract><trans-abstract xml:lang="en"><p>In the field of speech recognition, end-to-end models are gradually replacing traditional and hybrid approaches. Their main principle is autoregressive decoding, where the output sequence is formed from left to right. However, it has not yet been proven that this method provides the best results in converting speech to text. Moreover, end-toend models rely solely on the previous context, which complicates the processing of unclear or distorted sounds. In this regard, the insertion method was proposed, which does not use autoregressive decoding and generates output data in an arbitrary order. This paper examines a Kazakh speech recognition model trained using the insertion method and Connectionist Temporal Classification (CTC). The experiments conducted showed that this method improves recognition accuracy. Unlike autoregressive models, the Insertion method provides greater flexibility in processing sequences, as it does not require a strict order for generating output data. This reduces decoding delays and makes the model more robust to poorly pronounced words. Furthermore, combining the Insertion method with CTC improves the alignment of audio data and text transcription. This is especially important for agglutinative languages such as Kazakh. According to the experimental results, the recognition accuracy of the proposed model reached 10.2%, making it competitive today.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>коннекционная временная классификация</kwd><kwd>интегральные модели</kwd><kwd>распознавание казахской речи</kwd><kwd>Insertion</kwd><kwd>Transformer</kwd></kwd-group><kwd-group xml:lang="en"><kwd>connectionist temporal classification</kwd><kwd>end-to-end models</kwd><kwd>Kazakh speech recognition</kwd><kwd>insertion</kwd><kwd>transformer</kwd></kwd-group><funding-group xml:lang="ru"><funding-statement>Бұл зерттеу Қазақстан Республикасының Ғылым және жоғары білім министрлігі Ғылым комитеті тарапынан қаржыландырылды (Грант № BR24992875).</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Mamyrbayev, O., Oralbekova, D. Modern trends in the development of speech recognition systems. News of the National Academy of Sciences of the Republic of Kazakhstan, 4 (332), 42–51 (2020).</mixed-citation><mixed-citation xml:lang="en">Mamyrbayev, O., Oralbekova, D. Modern trends in the development of speech recognition systems. News of the National Academy of Sciences of the Republic of Kazakhstan, 4 (332), 42–51 (2020).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Graves, A., Fernandez, S., Gomez, F., and Schmidhuber, J. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. ICML, Pittsburgh, USA, pp. 369– 376 (2006).</mixed-citation><mixed-citation xml:lang="en">Graves, A., Fernandez, S., Gomez, F., and Schmidhuber, J. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. ICML, Pittsburgh, USA, pp. 369– 376 (2006).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Majhi, M.K., and Saha, S.K. An automatic speech recognition system in Odia language using attention mechanism and data augmentation. International Journal of Speech Technology, 27, 717–728 (2024). https://doi.org/10.1007/s10772-024-10132-6.</mixed-citation><mixed-citation xml:lang="en">Majhi, M.K., and Saha, S.K. An automatic speech recognition system in Odia language using attention mechanism and data augmentation. International Journal of Speech Technology, 27, 717–728 (2024). https://doi.org/10.1007/s10772-024-10132-6.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Cheng, L., Zhu, H., Hu, Z., and Luo, B. A Sequence-to-Sequence Model for Online Signal Detection and Format Recognition. IEEE Signal Processing Letters, 31, 994–998 (2024). https://doi.org/10.1109/LSP.2024.3384015.</mixed-citation><mixed-citation xml:lang="en">Cheng, L., Zhu, H., Hu, Z., and Luo, B. A Sequence-to-Sequence Model for Online Signal Detection and Format Recognition. IEEE Signal Processing Letters, 31, 994–998 (2024). https://doi.org/10.1109/LSP.2024.3384015.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Mundotiya, R.K., Mehta, A., Baruah, R., and Singh, A.K. Integration of morphological features and contextual weightage using monotonic chunk attention for part of speech tagging. Journal of King Saud University – Computer and Information Sciences, 34, 7324–7334 (2021).</mixed-citation><mixed-citation xml:lang="en">Mundotiya, R.K., Mehta, A., Baruah, R., and Singh, A.K. Integration of morphological features and contextual weightage using monotonic chunk attention for part of speech tagging. Journal of King Saud University – Computer and Information Sciences, 34, 7324–7334 (2021).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Deng, K., Cao, S., Zhang, Y., Ma, L., Cheng, G., Xu, J., and Zhang, P. Improving CTC-based speech recognition via knowledge transferring from pre-trained language models (2022). https://doi.org/10.48550/arXiv.2203.03582.</mixed-citation><mixed-citation xml:lang="en">Deng, K., Cao, S., Zhang, Y., Ma, L., Cheng, G., Xu, J., and Zhang, P. Improving CTC-based speech recognition via knowledge transferring from pre-trained language models (2022). https://doi.org/10.48550/arXiv.2203.03582.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Dingliwal, S., Sunkara, M., Ronanki, S., Farris, J., Kirchhoff, K., and Bodapati, S. Personalization of CTC Speech Recognition Models. 2022 IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar, pp. 302–309 (2023). https://doi.org/10.1109/SLT54892.2023.10022705.</mixed-citation><mixed-citation xml:lang="en">Dingliwal, S., Sunkara, M., Ronanki, S., Farris, J., Kirchhoff, K., and Bodapati, S. Personalization of CTC Speech Recognition Models. 2022 IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar, pp. 302–309 (2023). https://doi.org/10.1109/SLT54892.2023.10022705.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Zeyer, A., Kazuki, I., Ralf, S., and Hermann, N. Improved training of end-to-end attention models for speech recognition. arXiv preprint arXiv:1805.03294 (2018).</mixed-citation><mixed-citation xml:lang="en">Zeyer, A., Kazuki, I., Ralf, S., and Hermann, N. Improved training of end-to-end attention models for speech recognition. arXiv preprint arXiv:1805.03294 (2018).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Wang, Z., Tao, Z., Shao, Y., and Ding, B. LSTM-convolutional-BLSTM encoder-decoder network for minimum mean-square error approach to speech enhancement. Applied Acoustics, 172, 107647 (2021).</mixed-citation><mixed-citation xml:lang="en">Wang, Z., Tao, Z., Shao, Y., and Ding, B. LSTM-convolutional-BLSTM encoder-decoder network for minimum mean-square error approach to speech enhancement. Applied Acoustics, 172, 107647 (2021).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Huang, Z., Wang, P., Wang, J., Miao, H., Xu, J., and Zhang, P. Improving Transformer Based Endto-End Code-Switching Speech Recognition Using Language Identification. Applied Sciences, 11 (19), 9106 (2021). https://doi.org/10.3390/app11199106.</mixed-citation><mixed-citation xml:lang="en">Huang, Z., Wang, P., Wang, J., Miao, H., Xu, J., and Zhang, P. Improving Transformer Based Endto-End Code-Switching Speech Recognition Using Language Identification. Applied Sciences, 11 (19), 9106 (2021). https://doi.org/10.3390/app11199106.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Miao, H., Cheng, G., Gao, C., Zhang, P., and Yan, Y. Transformer-Based Online CTC/Attention EndTo-End Speech Recognition Architecture. ICASSP 2020 – 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6084–6088 (2020). https://doi.org/10.1109/ICASSP40776.2020.9053165.</mixed-citation><mixed-citation xml:lang="en">Miao, H., Cheng, G., Gao, C., Zhang, P., and Yan, Y. Transformer-Based Online CTC/Attention EndTo-End Speech Recognition Architecture. ICASSP 2020 – 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6084–6088 (2020). https://doi.org/10.1109/ICASSP40776.2020.9053165.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Li, F., Chen, J., and Zhang, X. A Survey of Non-Autoregressive Neural Machine Translation. Electronics, 12 (13), 2980 (2023). https://doi.org/10.3390/electronics12132980</mixed-citation><mixed-citation xml:lang="en">Li, F., Chen, J., and Zhang, X. A Survey of Non-Autoregressive Neural Machine Translation. Electronics, 12 (13), 2980 (2023). https://doi.org/10.3390/electronics12132980</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Chen, N., Watanabe, S., Villalba, J., and Dehak, N. Listen and fill in the missing letters: Nonautoregressive transformer for speech recognition. arXiv preprint arXiv:1911.04908 (2020).</mixed-citation><mixed-citation xml:lang="en">Chen, N., Watanabe, S., Villalba, J., and Dehak, N. Listen and fill in the missing letters: Nonautoregressive transformer for speech recognition. arXiv preprint arXiv:1911.04908 (2020).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Fujita, Y., Watanabe, S., Omachi, M., and Chan, X. Insertion-Based Modeling for End-to-End Automatic Speech Recognition. INTERSPEECH 2020 (2020). https://doi.org/10.48550/arXiv.2005.13211.</mixed-citation><mixed-citation xml:lang="en">Fujita, Y., Watanabe, S., Omachi, M., and Chan, X. Insertion-Based Modeling for End-to-End Automatic Speech Recognition. INTERSPEECH 2020 (2020). https://doi.org/10.48550/arXiv.2005.13211.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Rakhimova, D., Sagat, K., Zhakypbaeva, K., and Zhunussova, A. Development and Study of a Post-editing Model for Russian-Kazakh and English-Kazakh Translation Based on Machine Learning. In: Wojtkiewicz K., Treur J., Pimenidis E., Maleszka M. (eds) Advances in Computational Collective Intelligence. ICCCI 2021. Communications in Computer and Information Science, vol. 1463. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88113-9_42.</mixed-citation><mixed-citation xml:lang="en">Rakhimova, D., Sagat, K., Zhakypbaeva, K., and Zhunussova, A. Development and Study of a Post-editing Model for Russian-Kazakh and English-Kazakh Translation Based on Machine Learning. In: Wojtkiewicz K., Treur J., Pimenidis E., Maleszka M. (eds) Advances in Computational Collective Intelligence. ICCCI 2021. Communications in Computer and Information Science, vol. 1463. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88113-9_42.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Karyukin, V., Rakhimova, D., Karibayeva, A., Turganbayeva, A., and Turarbek, A. The neural machine translation models for the low-resource Kazakh–English language pair. PeerJ Computer Science, 9, e1224 (2023). https://doi.org/10.7717/peerj-cs.1224</mixed-citation><mixed-citation xml:lang="en">Karyukin, V., Rakhimova, D., Karibayeva, A., Turganbayeva, A., and Turarbek, A. The neural machine translation models for the low-resource Kazakh–English language pair. PeerJ Computer Science, 9, e1224 (2023). https://doi.org/10.7717/peerj-cs.1224</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Kydyrbekova, A., and Oralbekova, D. Speaker identification using distribution-preserving x-vector generation. News of the National Academy of Sciences of the Republic of Kazakhstan, Physico-mathematical series, 4 (352), 152–162 (2024). https://doi.org/10.32014/2024.2518-1726.314</mixed-citation><mixed-citation xml:lang="en">Kydyrbekova, A., and Oralbekova, D. Speaker identification using distribution-preserving x-vector generation. News of the National Academy of Sciences of the Republic of Kazakhstan, Physico-mathematical series, 4 (352), 152–162 (2024). https://doi.org/10.32014/2024.2518-1726.314</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Mamyrbayev, O., Alimhan, K., Oralbekova, D., Bekarystankyzy, A., and Zhumazhanov, B. Identifying the influence of transfer learning method in developing an end-to-end automatic speech recognition system with a low data level. Eastern-European Journal of Enterprise Technologies, 1 (9(115)), 84–92 (2022). https://doi.org/10.15587/1729-4061.2022.252801.</mixed-citation><mixed-citation xml:lang="en">Mamyrbayev, O., Alimhan, K., Oralbekova, D., Bekarystankyzy, A., and Zhumazhanov, B. Identifying the influence of transfer learning method in developing an end-to-end automatic speech recognition system with a low data level. Eastern-European Journal of Enterprise Technologies, 1 (9(115)), 84–92 (2022). https://doi.org/10.15587/1729-4061.2022.252801.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Mamyrbayev, O., Oralbekova, D., Kydyrbekova, A., Turdalykyzy, T., and Bekarystankyzy, A. End-to-End Model Based on RNN-T for Kazakh Speech Recognition. 2021 3rd International Conference on Computer Communication and the Internet (ICCCI), pp. 163–167 (2021). https://doi.org/10.1109/ICCCI51764.2021.9486811.</mixed-citation><mixed-citation xml:lang="en">Mamyrbayev, O., Oralbekova, D., Kydyrbekova, A., Turdalykyzy, T., and Bekarystankyzy, A. End-to-End Model Based on RNN-T for Kazakh Speech Recognition. 2021 3rd International Conference on Computer Communication and the Internet (ICCCI), pp. 163–167 (2021). https://doi.org/10.1109/ICCCI51764.2021.9486811.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Soleymanpour, M., Johnson, M.T., Soleymanpour, R., and Berry, J. Synthesizing Dysarthric Speech Using Multi-Speaker TTS for Dysarthric Speech Recognition. ICASSP 2022 – 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, pp. 7382–7386 (2022). https://doi.org/10.1109/ICASSP43922.2022.9746585.</mixed-citation><mixed-citation xml:lang="en">Soleymanpour, M., Johnson, M.T., Soleymanpour, R., and Berry, J. Synthesizing Dysarthric Speech Using Multi-Speaker TTS for Dysarthric Speech Recognition. ICASSP 2022 – 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, pp. 7382–7386 (2022). https://doi.org/10.1109/ICASSP43922.2022.9746585.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
