<?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">sibsutis</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник СибГУТИ</journal-title><trans-title-group xml:lang="en"><trans-title>The Herald of the Siberian State University of Telecommunications and Information Science</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1998-6920</issn><publisher><publisher-name>СибГУТИ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.55648/1998-6920-2021-15-4-23-31</article-id><article-id custom-type="elpub" pub-id-type="custom">sibsutis-67</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>Статьи</subject></subj-group></article-categories><title-group><article-title>Использование векторных представлений текста для синтеза эмоциональной речи</article-title><trans-title-group xml:lang="en"><trans-title>Emotional Speech Synthesis with Emotion Embeddings</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Болдаков</surname><given-names>В. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Boldakov</surname><given-names>V. ..</given-names></name></name-alternatives><email xlink:type="simple">valboldakov@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff xml:lang="ru" id="aff-1"><institution>СибГУТИ</institution><country>Russian Federation</country></aff><pub-date pub-type="collection"><year>2021</year></pub-date><pub-date pub-type="epub"><day>18</day><month>12</month><year>2021</year></pub-date><volume>0</volume><issue>4</issue><fpage>23</fpage><lpage>31</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Болдаков В.С., 2021</copyright-statement><copyright-year>2021</copyright-year><copyright-holder xml:lang="ru">Болдаков В.С.</copyright-holder><copyright-holder xml:lang="en">Boldakov V...</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.sibsutis.ru/jour/article/view/67">https://vestnik.sibsutis.ru/jour/article/view/67</self-uri><abstract><p>Исследуется возможность синтеза эмоциональной речи при помощи глобальных векторов стиля. Предлагается новый метод синтеза эмоциональной речи, использующий векторные представления эмоций на основе текстов. Демонстрируется реализация метода на авторегрессионной архитектуре Tacotron 2 и на базе трансформера FastSpeech 2.</p></abstract><trans-abstract xml:lang="en"><p>Several neural network architectures provide high-quality speech synthesis. Several neural network architectures provide high-quality speech synthesis. In this article, emotional speech synthesis with global style tokens is researched. A novel method of emotional speech synthesis with emotional text embeddings is described.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>синтез речи</kwd><kwd>нейронные сети</kwd><kwd>трансформер</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Tacotron 2</kwd><kwd>FastSpeech 2</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">Shen J., Pang R., Weiss R et al. Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions //2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, April 15 - April 20, 2018. P. 4779-4783.</mixed-citation><mixed-citation xml:lang="en">Shen J., Pang R., Weiss R et al. Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions //2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, April 15 - April 20, 2018. P. 4779-4783.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Ren Y., Hu C., Tan X. et al. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech. [Электронный ресурс]. URL: https://arxiv.org/abs/2006.04558 (дата обращения: 09.09.2021).</mixed-citation><mixed-citation xml:lang="en">Ren Y., Hu C., Tan X. et al. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech. [Электронный ресурс]. URL: https://arxiv.org/abs/2006.04558 (дата обращения: 09.09.2021).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Felbo B., Mislove A., SogaardA. etal. Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm // Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, September, 2017. P. 1615-1625.</mixed-citation><mixed-citation xml:lang="en">Felbo B., Mislove A., SogaardA. etal. Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm // Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, September, 2017. P. 1615-1625.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Wang Y, Stanton D., Zhang Y. et al. Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis. [Электронный ресурс]. URL: https://arxiv.org/abs/1803.09017 (дата обращения: 19.09.2021).</mixed-citation><mixed-citation xml:lang="en">Wang Y, Stanton D., Zhang Y. et al. Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis. [Электронный ресурс]. URL: https://arxiv.org/abs/1803.09017 (дата обращения: 19.09.2021).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">McAuliffe M., Socolof M., Mihuc S. et al. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi // INTERSPEECH 2017: Conference of the International Speech Communication Association, Stockholm, Sweden, August 20 - August 24, 2017. P. 498-502.</mixed-citation><mixed-citation xml:lang="en">McAuliffe M., Socolof M., Mihuc S. et al. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi // INTERSPEECH 2017: Conference of the International Speech Communication Association, Stockholm, Sweden, August 20 - August 24, 2017. P. 498-502.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Zhu X., Zhang Y., Yang S. et al. Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis // IEEE Access. 2019. V. 7. P. 65955-65964.</mixed-citation><mixed-citation xml:lang="en">Zhu X., Zhang Y., Yang S. et al. Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis // IEEE Access. 2019. V. 7. P. 65955-65964.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Болдаков В. С. Примеры синтеза эмоциональной речи на базе Tacotron 2. [Электронный ресурс]. URL: https://bit.ly/3nOPHRN (дата обращения: 09.09.2021).</mixed-citation><mixed-citation xml:lang="en">Болдаков В. С. Примеры синтеза эмоциональной речи на базе Tacotron 2. [Электронный ресурс]. URL: https://bit.ly/3nOPHRN (дата обращения: 09.09.2021).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Болдаков В. С. Примеры синтеза эмоциональной речи на базе FastSpeech 2. [Электронный ресурс]. URL: https://bit.ly/39i0T15 (дата обращения: 09.09.2021).</mixed-citation><mixed-citation xml:lang="en">Болдаков В. С. Примеры синтеза эмоциональной речи на базе FastSpeech 2. [Электронный ресурс]. URL: https://bit.ly/39i0T15 (дата обращения: 09.09.2021).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Ito K., Johnson L. The LJ Speech Dataset. [Электронный ресурс]. URL: https://keithito.com/LJ-Speech-Dataset/(дата обращения: 09.09.2021).</mixed-citation><mixed-citation xml:lang="en">Ito K., Johnson L. The LJ Speech Dataset. [Электронный ресурс]. URL: https://keithito.com/LJ-Speech-Dataset/(дата обращения: 09.09.2021).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Luo L., Wang Y. et al. EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification. [Электронный ресурс]. URL: https://arxiv.org/pdf/1907.09669.pdf (дата обращения: 19.09.2021).</mixed-citation><mixed-citation xml:lang="en">Luo L., Wang Y. et al. EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classification. [Электронный ресурс]. URL: https://arxiv.org/pdf/1907.09669.pdf (дата обращения: 19.09.2021).</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>
