<?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">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2026-26-2-295-305</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-591</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 СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</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>Спектральные многополосные рекуррентные нейронные сети для моделирования компрессоров динамического диапазона методом «черного ящика»</article-title><trans-title-group xml:lang="en"><trans-title>Spectral-based multi-band recurrent neural networks for black-box modeling of dynamic range compressors</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0003-1554-2873</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Балыкин</surname><given-names>А. Ф.</given-names></name><name name-style="western" xml:lang="en"><surname>Balykin</surname><given-names>A. F.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Балыкин Андрей Федорович — аспирант</p><p>Санкт-Петербург, 199034</p><p>sc 58548795200</p></bio><bio xml:lang="en"><p>Andrei F. Balykin — PhD Student</p><p>Saint Petersburg, 199034</p><p>sc 58548795200</p></bio><email xlink:type="simple">st054659@student.spbu.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/0000-0002-7305-1429</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Блеканов</surname><given-names>И. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Blekanov</surname><given-names>I. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Блеканов Иван Станиславович — кандидат технических наук, доцент, заведующий кафедрой</p><p>Санкт-Петербург, 199034</p><p>sc 56149559700</p></bio><bio xml:lang="en"><p>Ivan S. Blekanov — PhD, Associate Professor</p><p>Saint Petersburg, 199034</p><p>sc 56149559700</p></bio><email xlink:type="simple">i.blekanov@spbu.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>St. Petersburg State University (SPbU)</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>20</day><month>04</month><year>2026</year></pub-date><volume>26</volume><issue>2</issue><fpage>295</fpage><lpage>305</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Балыкин А.Ф., Блеканов И.С., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Балыкин А.Ф., Блеканов И.С.</copyright-holder><copyright-holder xml:lang="en">Balykin A.F., Blekanov I.S.</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://ntv.elpub.ru/jour/article/view/591">https://ntv.elpub.ru/jour/article/view/591</self-uri><abstract><p>Введение. Подходы глубокого обучения все активнее применяются для задач виртуального аналогового моделирования, цель которых заключается в воспроизведении звуковых характеристик аналоговых аудиоустройств. В области моделирования аналоговых компрессоров динамического диапазона многие существующие методы работают с аудиосигналами во временной области, что обуславливает высокую размерность входного сигнала при высокой частоте дискретизации. Обработка таких высокодетализированных признаков является вычислительно затратной и снижает эффективность моделей. Метод. Представлен метод предварительной обработки признаков, использующий амплитудную компоненту кратковременного преобразования Фурье в сочетании с механизмом спектрального усиления, функционирующим аналогично спектральной маске, но способным как ослаблять, так и усиливать частотные компоненты. В качестве рассматриваемых архитектур были предложены многополосные сети Long Short-Term Memory (LSTM) и Gated Recurrent Unit (GRU), которые разделяют амплитудный спектр на несколько частотных полос для независимой обработки, что существенно снижает вычислительную сложность при сохранении высокой точности моделирования. Основные результаты. Для оценки представленного подхода были сформированы два набора данных, содержащих записи с аналогового компрессора Alesis 3630 и его цифровой эмуляции discoDSP NightShine. На выбранных наборах данных были проведены эксперименты, в которых предложенный метод сравнивался с базовыми моделями по четырем объективным метрикам, теоретическим и эмпирическим показателям вычислительной производительности, а также результатам субъективного прослушивания. Обсуждение. Результаты показали, что однополосные модели с использованием разработанного метода извлечения признаков превосходят базовые модели по всем оценочным метрикам. Многополосные конфигурации обеспечивают более выгодный баланс между качеством и вычислительной эффективностью. В частности, четырехполосные архитектуры LSTM и GRU демонстрируют более высокую перцептивную точность при существенно меньших вычислительных затратах. Кроме того, был проведен субъективный тест прослушивания, результаты которого согласуются с объективными метриками. Исходный код и предобученные модели опубликованы в открытом доступе для обеспечения воспроизводимости результатов.</p></abstract><trans-abstract xml:lang="en"><p>Deep learning approaches have been increasingly adopted for virtual analog modeling, which aims to replicate the sonic characteristics of analog audio devices. In the context of analog dynamic range compressor modeling, many existing methods operate directly on raw audio waveforms which are high-dimensional and contain fine-grained temporal features at high sampling rates. These representations are computationally demanding and limit model efficiency. We propose a feature extraction pipeline that leverages the magnitude component of the Short-Time Fourier Transform in combination with a spectral amplification mechanism which acts similarly to a spectral mask but can both attenuate and amplify selected frequency components. We employ multi-band Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures that split the magnitude spectrum into several frequency bands for independent processing, substantially reducing computational complexity while preserving high modeling accuracy. To evaluate our approach, we created two datasets consisting of recordings of the consumer-grade analog compressor Alesis 3630 and its digital counterpart, discoDSP NightShine. We conducted extensive experiments comparing our method against raw waveform baselines using four objective metrics, theoretical and empirical measurements of computational performance, and a subjective listening test. Results indicate that single-band models based on the proposed feature extraction pipeline outperform raw-audio baselines across all evaluation metrics. Multi-band configurations further improve the efficiency balance. In particular, four-band LSTM and GRU architectures achieve higher perceptual fidelity at substantially lower computational cost. Moreover, we conducted a subjective listening test that yielded results aligned with the objective metrics. All source code and pretrained models are provided for reproducibility.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>обработка сигналов</kwd><kwd>глубокое обучение</kwd><kwd>виртуальное аналоговое моделирование</kwd><kwd>метод черного ящика</kwd><kwd>рекуррентные нейронные сети</kwd></kwd-group><kwd-group xml:lang="en"><kwd>signal processing</kwd><kwd>deep learning</kwd><kwd>virtual analog modeling</kwd><kwd>black-box modeling</kwd><kwd>recurrent neural networks</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Wilmering T., Moffat D., Milo A., Sandler M. A history of audio effects. Applied Sciences, 2020, vol. 10, no. 3, pp. 791. https://doi.org/10.3390/app10030791</mixed-citation><mixed-citation xml:lang="en">Wilmering T., Moffat D., Milo A., Sandler M. A history of audio effects. Applied Sciences, 2020, vol. 10, no. 3, pp. 791. https://doi.org/10.3390/app10030791</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Montenegro J. Design of an audio compressor with digital control. TECCIENCIA, 2021, vol. 16, no. 30, pp. 51–64. https://doi. org/10.18180/tecciencia.2021.30.4</mixed-citation><mixed-citation xml:lang="en">Montenegro J. Design of an audio compressor with digital control. TECCIENCIA, 2021, vol. 16, no. 30, pp. 51–64. https://doi. org/10.18180/tecciencia.2021.30.4</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Välimäki V., Reiss J. All about audio equalization: solutions and frontiers. Applied Sciences, 2016, vol. 6, no. 5, pp. 129. https://doi.org/10.3390/app6050129</mixed-citation><mixed-citation xml:lang="en">Välimäki V., Reiss J. All about audio equalization: solutions and frontiers. Applied Sciences, 2016, vol. 6, no. 5, pp. 129. https://doi.org/10.3390/app6050129</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Réveillac J.-M. Musical Sound Effects: Analog and Digital Sound Processing. Wiley-ISTE, 2017, 558 p.</mixed-citation><mixed-citation xml:lang="en">Réveillac J.-M. Musical Sound Effects: Analog and Digital Sound Processing. Wiley-ISTE, 2017, 558 p.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Chowdhury J. A comparison of virtual analog modelling techniques for desktop and embedded implementations. arXiv, 2020. arXiv:2009.02833. https://doi.org/10.48550/arXiv.2009.02833</mixed-citation><mixed-citation xml:lang="en">Chowdhury J. A comparison of virtual analog modelling techniques for desktop and embedded implementations. arXiv, 2020. arXiv:2009.02833. https://doi.org/10.48550/arXiv.2009.02833</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Purwins H., Li B., Virtanen T., Schlüter J., Chang S.-Y., Sainath T. Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing, 2019, vol. 13, no. 2, pp. 206–219. https://doi.org/10.1109/jstsp.2019.2908700</mixed-citation><mixed-citation xml:lang="en">Purwins H., Li B., Virtanen T., Schlüter J., Chang S.-Y., Sainath T. Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing, 2019, vol. 13, no. 2, pp. 206–219. https://doi.org/10.1109/jstsp.2019.2908700</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Liu X., Sahidullah M., Kinnunen T. A comparative re-assessment of feature extractors for deep speaker embeddings. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2020, pp. 3221–3225. https://doi.org/10.21437/interspeech.2020-1765</mixed-citation><mixed-citation xml:lang="en">Liu X., Sahidullah M., Kinnunen T. A comparative re-assessment of feature extractors for deep speaker embeddings. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2020, pp. 3221–3225. https://doi.org/10.21437/interspeech.2020-1765</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Sun Y., Yang L., Zhu H., Hao J. Funnel deep complex U-Net for phase-aware speech enhancement. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2021, pp. 161–165. https://doi.org/10.21437/Interspeech.2021-10</mixed-citation><mixed-citation xml:lang="en">Sun Y., Yang L., Zhu H., Hao J. Funnel deep complex U-Net for phase-aware speech enhancement. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2021, pp. 161–165. https://doi.org/10.21437/Interspeech.2021-10</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Kong J., Kim J., Bae J. HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis. Proc. of the 34th International Conference on Neural Information Processing Systems, 2020, pp. 17022–17033.</mixed-citation><mixed-citation xml:lang="en">Kong J., Kim J., Bae J. HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis. Proc. of the 34th International Conference on Neural Information Processing Systems, 2020, pp. 17022–17033.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Zölzer U. DAFX: Digital Audio Effects. Wiley, 2011, 624 p</mixed-citation><mixed-citation xml:lang="en">Zölzer U. DAFX: Digital Audio Effects. Wiley, 2011, 624 p</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Kates J.M. Principles of digital dynamic-range compression. Trends in Amplification, 2005, vol. 9, no. 2, pp. 45–76. https://doi.org/10.1177/108471380500900202</mixed-citation><mixed-citation xml:lang="en">Kates J.M. Principles of digital dynamic-range compression. Trends in Amplification, 2005, vol. 9, no. 2, pp. 45–76. https://doi.org/10.1177/108471380500900202</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Giannoulis D., Massberg M., Reiss J.D. Digital dynamic range compressor design—A tutorial and analysis. Journal of the Audio Engineering Society, 2012, vol. 60, no. 6, pp. 399–408.</mixed-citation><mixed-citation xml:lang="en">Giannoulis D., Massberg M., Reiss J.D. Digital dynamic range compressor design—A tutorial and analysis. Journal of the Audio Engineering Society, 2012, vol. 60, no. 6, pp. 399–408.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">D’Angelo S. Lightweight virtual analog modeling. Proc. of the 22nd Colloquio di Informatica Musicale (CIM), 2018.</mixed-citation><mixed-citation xml:lang="en">D’Angelo S. Lightweight virtual analog modeling. Proc. of the 22nd Colloquio di Informatica Musicale (CIM), 2018.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Eichas F., Zölzer U. Virtual analog modeling of guitar amplifiers with Wiener–Hammerstein models. Proc.of the 44th Annual Convention on Acoustics (DAGA), 2018.</mixed-citation><mixed-citation xml:lang="en">Eichas F., Zölzer U. Virtual analog modeling of guitar amplifiers with Wiener–Hammerstein models. Proc.of the 44th Annual Convention on Acoustics (DAGA), 2018.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Cheng C.M., Peng Z.K., Zhang W.M., Meng G. Volterra-series-based nonlinear system modeling and its engineering applications: A stateof- the-art review. Mechanical Systems and Signal Processing, 2017, vol. 87, part A. pp. 340–364. https://doi.org/10.1016/j.ymssp.2016.10.029</mixed-citation><mixed-citation xml:lang="en">Cheng C.M., Peng Z.K., Zhang W.M., Meng G. Volterra-series-based nonlinear system modeling and its engineering applications: A stateof- the-art review. Mechanical Systems and Signal Processing, 2017, vol. 87, part A. pp. 340–364. https://doi.org/10.1016/j.ymssp.2016.10.029</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">van den Oord A., Dieleman S., Zen H., Simonyan K., Vinyals O., Graves A., et al. WaveNet: A generative model for raw audio. arXiv, 2016. arXiv:1609.03499. https://doi.org/10.48550/arXiv.1609.03499</mixed-citation><mixed-citation xml:lang="en">van den Oord A., Dieleman S., Zen H., Simonyan K., Vinyals O., Graves A., et al. WaveNet: A generative model for raw audio. arXiv, 2016. arXiv:1609.03499. https://doi.org/10.48550/arXiv.1609.03499</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Wright A., Damskägg E.-P., Välimäki V. Real-time black-box modelling with recurrent neural networks. Proc. of the 22nd International Conference on Digital Audio Effects (DAFx-19), 2019, pp. 1–9.</mixed-citation><mixed-citation xml:lang="en">Wright A., Damskägg E.-P., Välimäki V. Real-time black-box modelling with recurrent neural networks. Proc. of the 22nd International Conference on Digital Audio Effects (DAFx-19), 2019, pp. 1–9.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Ramirez M.A.M., Benetos E., Reiss J.D. Deep learning for black-box modeling of audio effects. Applied Sciences, 2020, vol. 10, no. 2, pp. 638. https://doi.org/10.3390/app10020638</mixed-citation><mixed-citation xml:lang="en">Ramirez M.A.M., Benetos E., Reiss J.D. Deep learning for black-box modeling of audio effects. Applied Sciences, 2020, vol. 10, no. 2, pp. 638. https://doi.org/10.3390/app10020638</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Damskägg E.-P., Juvela L., Välimäki V. Real-time modeling of audio distortion circuits with deep learning. Proc. of the 16th Sound and Music Computing Conference, 2019, pp. 332–339.</mixed-citation><mixed-citation xml:lang="en">Damskägg E.-P., Juvela L., Välimäki V. Real-time modeling of audio distortion circuits with deep learning. Proc. of the 16th Sound and Music Computing Conference, 2019, pp. 332–339.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Hawley S.H., Colburn B., Mimilakis S.I. SignalTrain: profiling audio compressors with deep neural networks. arXiv, 2019. arXiv:1905.11928. https://doi.org/10.48550/arXiv.1905.11928</mixed-citation><mixed-citation xml:lang="en">Hawley S.H., Colburn B., Mimilakis S.I. SignalTrain: profiling audio compressors with deep neural networks. arXiv, 2019. arXiv:1905.11928. https://doi.org/10.48550/arXiv.1905.11928</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Steinmetz C.J., Reiss J.D. Efficient neural networks for real-time analog audio effect modeling. arXiv, 2021. arXiv:2102.06200. https://doi.org/10.48550/arXiv.2102.06200</mixed-citation><mixed-citation xml:lang="en">Steinmetz C.J., Reiss J.D. Efficient neural networks for real-time analog audio effect modeling. arXiv, 2021. arXiv:2102.06200. https://doi.org/10.48550/arXiv.2102.06200</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Simionato R., Fasciani S. Fully conditioned and low-latency blackbox modeling of analog compression. Proc. of the International Conference on Digital Audio Effects Dafx, 2023.</mixed-citation><mixed-citation xml:lang="en">Simionato R., Fasciani S. Fully conditioned and low-latency blackbox modeling of analog compression. Proc. of the International Conference on Digital Audio Effects Dafx, 2023.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Yin H., Cheng G., Steinmetz C.J., Yuan R., Stern R.M., Dannenberg R.B. Modeling analog dynamic range compressors using deep learning and state-space models. arXiv, 2024. arXiv:2403.16331. https://doi.org/10.48550/arXiv.2403.16331</mixed-citation><mixed-citation xml:lang="en">Yin H., Cheng G., Steinmetz C.J., Yuan R., Stern R.M., Dannenberg R.B. Modeling analog dynamic range compressors using deep learning and state-space models. arXiv, 2024. arXiv:2403.16331. https://doi.org/10.48550/arXiv.2403.16331</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Simionato R., Fasciani S. Modeling time-variant responses of optical compressors with selective state space models. AES Journal of the Audio Engineering Society, 2025, vol. 73, no. 3. pp. 144–165. https://doi.org/10.17743/jaes.2022.0194</mixed-citation><mixed-citation xml:lang="en">Simionato R., Fasciani S. Modeling time-variant responses of optical compressors with selective state space models. AES Journal of the Audio Engineering Society, 2025, vol. 73, no. 3. pp. 144–165. https://doi.org/10.17743/jaes.2022.0194</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Fonseca E., Favory X., Pons J., Font F., Serra X. FSD50K: An open dataset of human-labeled sound events. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, vol. 30, pp. 829–852. https://doi.org/10.1109/taslp.2021.3133208</mixed-citation><mixed-citation xml:lang="en">Fonseca E., Favory X., Pons J., Font F., Serra X. FSD50K: An open dataset of human-labeled sound events. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, vol. 30, pp. 829–852. https://doi.org/10.1109/taslp.2021.3133208</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Yamagishi J., Veaux C., MacDonald K. CSTR VCTK corpus: English multi-speaker corpus for CSTR Voice Cloning Toolkit (version 0.92). University of Edinburgh, Centre for Speech Technology Research (CSTR), 2019, https://doi.org/10.7488/ds/2645</mixed-citation><mixed-citation xml:lang="en">Yamagishi J., Veaux C., MacDonald K. CSTR VCTK corpus: English multi-speaker corpus for CSTR Voice Cloning Toolkit (version 0.92). University of Edinburgh, Centre for Speech Technology Research (CSTR), 2019, https://doi.org/10.7488/ds/2645</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>
