ntvНаучно-технический вестник информационных технологий, механики и оптикиScientific and Technical Journal of Information Technologies, Mechanics and Optics2226-14942500-0373Университет ИТМО10.17586/2226-1494-2026-26-3-447-456ntv-612Research ArticleОБЗОРНЫЕ СТАТЬИREVIEW PAPERSАналитический обзор методов сквозного перевода речи на основе акустико-семантических представленийAnalytical review of end-to-end speech translation methods based on acoustic-semantic representationshttps://orcid.org/0009-0003-8313-3780ОстровскийА. О.OstrovskiiA. O.

Островский Артём Олегович — младший научный сотрудник

Санкт-Петербург,199178

Artem O. Ostrovskii — Junior Researcher

Saint Petersburg, 199178

ostrovskii.a@iias.spb.suhttps://orcid.org/0000-0003-3424-652XКарповА. А.KarpovA. A.

Карпов Алексей Анатольевич — доктор технических наук, профессор, руководитель лаборатории

Санкт-Петербург,199178

Alexey A. Karpov — D.Sc., Professor, Head of Laboratory

Saint Petersburg, 199178

karpov@iias.spb.suСанкт-Петербургский Федеральный исследовательский центр Российской академии наукРоссияSt. Petersburg Federal Research Center of the Russian Academy of SciencesRussian Federation202609072026263447456Copyright © Островский А.О., Карпов А.А., 20262026Островский А.О., Карпов А.А.Ostrovskii A.O., Karpov A.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ntv.elpub.ru/jour/article/view/612

Введение. Выполнен анализ современных методов сквозного перевода речи, использующих дискретные представления речевого сигнала в качестве промежуточного. Актуальность темы обусловлена растущим спросом на системы машинного перевода речи в реальном времени, способным сохранять уникальные голосовые характеристики диктора. Рассмотрены подходы, выполняющие межъязыковое преобразование речи в речь без промежуточного перехода к тексту. Особое внимание уделено роли дискретных единиц как носителей семантической и паралингвистической информации, а также их значению в архитектурах сквозного перевода речи. Метод. Проведен систематический обзор и сравнительный анализ более 50 научных публикаций за период 2012–2025 гг. Представлен анализ архитектур прямого перевода речи, методов самоконтролируемого обучения представлений, нейросетевых аудиокодеков и мультиязычных систем масштабирования. Для каждого класса методов выделены принципы построения, достоинства и ограничения. Рассмотрены основные корпуса данных и показатели оценки качества перевода. Основные результаты. Показано, что переход от каскадных архитектур машинного перевода к сквозным методам позволяет сократить накопление ошибок и снизить задержку при переводе. Подтверждено, что при использовании предобучения, качество синтеза речи в сквозных системах приближается к каскадным. Дискретные акустические единицы, получаемые методами самоконтролируемого обучения и нейросетевыми кодеками, способны сохранять информацию, необходимую для восстановления семантического содержания и индивидуальных характеристик речи. Выявлены ключевые исследовательские пробелы: в большинстве исследованных научных работ дискретные представления используются как технический инструмент, тогда как их внутренняя структура, лингвистическая интерпретируемость и информационная емкость остаются недостаточно изученными. Обсуждение. Результаты обзора могут быть использованы при проектировании систем синхронного машинного перевода с сохранением голосовых характеристик говорящего. Сформулированы направления дальнейших исследований в области анализа внутренней структуры дискретных представлений, разработки методов контролируемого переноса паралингвистических характеристик между языками, а также создание метрик для раздельной оценки семантической точности и качества сохранения просодии при переводе. Полученные выводы представляют интерес как для фундаментальных исследований, так и для прикладных задач разработки систем машинного перевода.

This paper analyzes contemporary methods of end-to-end speech-to-speech translation that employ discrete representations of the speech signal as an intermediate representation. The relevance of the topic is driven by the growing demand for real-time machine speech translation systems capable of preserving the unique vocal characteristics of the speaker. The study examines approaches that perform cross-lingual speech-to-speech conversion without an intermediate transition to text. Particular attention is paid to the role of discrete units as carriers of semantic and paralinguistic information as well as their significance in end-to-end speech translation architectures. A systematic review and comparative analysis of the literature covering the period 2012–2025, encompassing more than 50 publications, was conducted. Direct speech translation architectures, self-supervised representation learning methods, neural audio codecs, and multilingual scaling systems were analyzed. For each class of methods, the design principles, advantages, and limitations were identified. The main data corpora and translation quality evaluation metrics were reviewed. It is shown that the transition from cascaded machine translation architectures to end-to-end methods reduces error accumulation and decreases translation latency. It is further demonstrated that, when pre-training is employed, the speech synthesis quality of end-to-end systems approaches that of cascaded ones. Discrete acoustic units obtained via self-supervised learning methods and neural codecs are capable of preserving the information necessary for recovering semantic content and individual speech characteristics. Key research gaps have been identified: in the majority of works, discrete representations are used as a technical tool, while their internal structure, linguistic interpretability, and information capacity remains insufficiently studied. The findings of the review may be applied in the design of simultaneous machine translation systems that preserve the vocal characteristics of the speaker. Directions for further research have been formulated, including analysis of the internal structure of discrete representations, development of methods for controlled cross-lingual transfer of paralinguistic characteristics, and the creation of metrics for separately evaluating semantic accuracy and prosody preservation quality in translation. The conclusions obtained are of interest both for fundamental research and for applied problems in the development of machine translation systems.

машинный перевод речи в речьсквозные моделидискретные представления речинейросетевой синтезпаралингвистические характеристики речиspeech-to-speech translationend-to-end modelsdiscrete speech representationsneural speech synthesisparalinguistic featuresРабота выполнена в рамках бюджетной темы СПб ФИЦ РАН № FFZF-2025-0003.This research was supported by the Russian state research topic of SPC RAS No. FFZF-2025-0003.ReferencesSethiya N., Maurya C.K. End-to-end speech-to-text translation: a survey // Computer Speech & Language. 2025. V. 90. P. 101751. doi: 10.1016/j.csl.2024.101751Sethiya N., Maurya C.K. End-to-end speech-to-text translation: a survey. Computer Speech & Language, 2025, vol. 90, pp. 101751. doi: 10.1016/j.csl.2024.101751Bentivogli L., Cettolo M., Gaido M., Karakanta A., Martinelli A., Negri M., et al. Cascade versus direct speech translation: Do the differences still make a difference? // Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021. P. 2873–2887. doi: 10.18653/v1/2021.acl-long.224Bentivogli L., Cettolo M., Gaido M., Karakanta A., Martinelli A., Negri M., Turchi M. Cascade versus direct speech translation: Do the differences still make a difference? Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021, pp. 2873–2887. doi: 10.18653/v1/2021.acl-long.224Jia Y., Weiss R.J., Biadsy F., Macherey W., Johnson M., Chen Z., et al. Direct speech-to-speech translation with a sequence-to-sequence model // Proc. of the Annual Conference of the International Speech Communication Association Interspeech. 2019. P. 1123–1127. doi: 10.21437/Interspeech.2019-1951Jia Y., Weiss R.J., Biadsy F., Macherey W., Johnson M., Chen Z., Wu Y. Direct speech-to-speech translation with a sequence-tosequence model. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2019, pp. 1123-1127. doi: 10.21437/Interspeech.2019-1951Lee A., Chen P.-J., Wang C., Gu J., Popuri S., et al. Direct speech-tospeech translation with discrete units // Proc. of the 60th Annual Meeting of the Association for Computational Linguistics. 2022. V. 1. P. 3327–3339. doi: 10.18653/v1/2022.acl-long.235Lee A., Chen P.-J., Wang C., Gu J., Popuri S., et al. Direct speech-to speech translation with discrete units. Proc. of the 60th Annual Meeting of the Association for Computational Linguistics, 2022, vol. 1, pp. 3327–3339. doi: 10.18653/v1/2022.acl-long.235Lee A., Gong H., Duquenne P.-A., Schwenk H., Chen P.-J., Wang C., et al. Textless speech-to-speech translation on real data // Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022. P. 860–872. doi: 10.18653/v1/2022.naacl-main.63Lee A., Gong H., Duquenne P.-A., Schwenk H., Chen P.-J., Wang C., et al. Textless speech-to-speech translation on real data. Proc. of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022, pp. 860–872. doi: 10.18653/v1/2022.naacl-main.63Baevski A., Schneider S., Auli M. vq-wav2vec: Self-supervised learning of discrete speech representations // Proc. of the International Conference on Learning Representations. 2020.Baevski A., Schneider S., Auli M. vq-wav2vec: Self-supervised learning of discrete speech representations. Proc. of the International Conference on Learning Representations, 2020.Baevski A., Zhou Y., Mohamed A., Auli M. wav2vec 2.0: A framework for self-supervised learning of speech representations // Advances in Neural Information Processing Systems. 2020. V. 33. P. 12449–12460.Baevski A., Zhou Y., Mohamed A., Auli M. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, 2020, vol. 33. P. 12449–12460.Hsu W.-N., Bolte B., Tsai Y.-H.H., Lakhotia K., Salakhutdinov R., Mohamed A. HuBERT: Self-supervised speech representation learning by masked prediction of hidden units // IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2021. V. 29. P. 3451–3460. doi: 10.1109/TASLP.2021.3122291Hsu W.-N., Bolte B., Tsai Y.-H.H., Lakhotia K., Salakhutdinov R., Mohamed A. HuBERT: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, vol. 29, pp. 3451–3460. doi: 10.1109/TASLP.2021.3122291Chen S., Wang C., Chen Z., Wu Y., Liu S., Chen Z., et al. WavLM: Large-scale self-supervised pre-training for full stack speech processing // IEEE Journal of Selected Topics in Signal Processing. 2022. V. 16. N 6. P. 1505–1518. doi: 10.1109/JSTSP.2022.3188113Chen S., Wang C., Chen Z., Wu Y., Liu S., Chen Z., et al. WavLM: Large-scale self-supervised pre-training for full stack speech processing. IEEE Journal of Selected Topics in Signal Processing, 2022, vol. 16, no. 6, pp. 1505–1518. doi: 10.1109/JSTSP.2022.3188113Zeghidour N., Luebs A., Omran A., Skoglund J., Tagliasacchi M. SoundStream: an end-to-end neural audio codec // IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2021. V. 30. P. 495–507. doi: 10.1109/TASLP.2021.3129994Zeghidour N., Luebs A., Omran A., Skoglund J., Tagliasacchi M. SoundStream: an end-to-end neural audio codec. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, vol. 30, pp. 495–507. doi: 10.1109/TASLP.2021.3129994Défossez A., Copet J., Synnaeve G., Adi Y. High fidelity neural audio compression // arXiv. 2022. arXiv:2210.13438. doi: 10.48550/arXiv.2210.13438Défossez A., Copet J., Synnaeve G., Adi Y. High fidelity neural audio compression. arXiv, 2022. arXiv:2210.13438. doi: 10.48550/arXiv.2210.13438Chen S., Wang C., Wu Y., Zhang Z., Zhou L., Liu S., et al. Neural codec language models are zero-shot text to speech synthesizers // IEEE Transactions on Audio, Speech and Language Processing. 2025. V. 33. P. 705–718. doi: 10.1109/TASLPRO.2025.3530270Chen S., Wang C., Wu Y., Zhang Z., Zhou L., Liu S., et al. Neural codec language models are zero-shot text to speech synthesizers. IEEE Transactions on Audio, Speech and Language Processing, 2025, vol. 33, pp. 705–718. doi: 10.1109/TASLPRO.2025.3530270Inaguma H., Popuri S., Kulikov I., Chen P.-J., Wang C., Chung Y.-A., et al. UnitY: Two-pass direct speech-to-speech translation with discrete units // Proc. of the 61st Annual Meeting of the Association for Computational Linguistics. 2023. P. 15655–15680. doi: 10.18653/v1/2023.acl-long.872Inaguma H., Popuri S., Kulikov I., Chen P.-J., Wang C., Chung Y.-A., et al. UnitY: Two-pass direct speech-to-speech translation with discrete units. Proc. of the 61st Annual Meeting of the Association for Computational Linguistics, 2023, pp. 15655–15680. doi: 10.18653/v1/2023.acl-long.872Barrault L., Chung Y.-A., Meglioli M.C., Dale D., Dong N., Duquenne P.-A., et al. SeamlessM4T: Massively multilingual & multimodal machine translation // arXiv. 2023. arXiv:2308.11596. doi:10.48550/arXiv.2308.11596SeamlessM4T: Massively multilingual & multimodal machine translation. arXiv, 2023. arXiv:2308.11596. doi: 10.48550/arXiv.2308.11596Jia Y., Ramanovich M.T., Remez T., Pomerantz R. Translatotron 2: High-quality direct speech-to-speech translation with voice preservation // Proc. of the 39th International Conference on Machine Learning. 2022. V. 162. P. 10120–10134.Jia Y., Ramanovich M.T., Remez T., Pomerantz R. Translatotron 2: High-quality direct speech-to-speech translation with voice preservation. Proc. of the 39th International Conference on Machine Learning, 2022, vol. 162, pp. 10120–10134.Nachmani E., Levkovitch A., Ding Y., Asawaroengchai C., Zen H., Ramanovich M.T. Translatotron 3: Speech to speech translation with monolingual data // Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2024. P. 1068610690. doi: 10.1109/ICASSP48485.2024.10448426Nachmani E., Levkovitch A., Ding Y., Asawaroengchai C., Zen H., Ramanovich M.T. Translatotron 3: Speech to speech translation with monolingual data. Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 1068610690. doi: 10.1109/ICASSP48485.2024.10448426Costa-jussà M.R., Cross J., Çelebi O., Elbayad M., Heafield K., Heffernan K. et al., No language left behind: Scaling human-centered machine translation // arXiv. 2022. arXiv:2207.04672. doi: 10.48550/arXiv.2207.04672Costa-jussà M.R., Cross J., Çelebi O., Elbayad M., Heafield K., Heffernan K. et al., No language left behind: Scaling human-centered machine translation. arXiv, 2022. arXiv:2207.04672. doi: 10.48550/arXiv.2207.04672Barrault L., Chung Y.-A., Meglioli M.C., Dale D., Dong N., Duppenthaler M., et al. Seamless: Multilingual expressive and streaming speech translation // arXiv. 2023. arXiv:2312.05187. doi: 10.48550/arXiv.2312.05187Barrault L., Chung Y.-A., Meglioli M.C., Dale D., Dong N., Duppenthaler M., et al. Seamless: Multilingual expressive and streaming speech translation. arXiv, 2023. arXiv:2312.05187. doi: 10.48550/arXiv.2312.05187Карпов А.А., Верходанова В.О. Автоматическая обработка звучащей речи для малоресурсных языков мира // Вопросы языкознания. 2015. № 2. С. 117–135.Karpov A.A., Verkhodanova V.O. Speech technologies for underresourced languages of the world. Voprosy Jazykoznanija, 2015, no. 2, pp. 117–135. (in Russian)Rubenstein P.K., Asawaroengchai C., Nguyen D.D., Bapna A., Borsos Z., de Chaumont Quitry F., et al. AudioPaLM: A large language model that can speak and listen // arXiv. 2023. arXiv:2306.12925. doi: 10.48550/arXiv.2306.12925Rubenstein P.K., Asawaroengchai C., Nguyen D.D., Bapna A., Borsos Z., de Chaumont Quitry F., et al. AudioPaLM: A large language model that can speak and listen. arXiv, 2023. arXiv:2306.12925. doi: 10.48550/arXiv.2306.12925Borsos Z., Marinier R., Vincent D., Kharitonov E., Pietquin O., Sharifi M., et al. AudioLM: A language modeling approach to audio generation // IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2023. V. 31. P. 2523–2533. doi: 10.1109/TASLP.2023.3288409Borsos Z., Marinier R., Vincent D., Kharitonov E., Pietquin O., Sharifi M., et al. AudioLM: A language modeling approach to audio generation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023, vol. 31, pp. 2523–2533. doi: 10.1109/TASLP.2023.3288409Zhang D., Li S., Zhang X., Zhan J., Wang P., Zhou Y., et al. SpeechGPT: Empowering large language models with intrinsic crossmodal conversational abilities // Findings of the Association for Computational Linguistics: EMNLP. 2023. P. 15757–15773. doi: 10.18653/v1/2023.findings-emnlp.1055Zhang D., Li S., Zhang X., Zhan J., Wang P., Zhou Y., et al. SpeechGPT: Empowering large language models with intrinsic crossmodal conversational abilities. Findings of the Association for Computational Linguistics: EMNLP, 2023, pp. 15757–15773. doi: 10.18653/v1/2023.findings-emnlp.1055Zeng A., Du Z., Liu M., Wang K., Jiang S., Zhao L., et al. GLM-4Voice: Towards intelligent and human-like end-to-end spoken chatbot // arXiv. 2024. arXiv:2412.02612. 2024. doi: 10.48550/arXiv.2412.02612Zeng A., Du Z., Liu M., Wang K., Jiang S., Zhao L., et al. GLM-4Voice: Towards intelligent and human-like end-to-end spoken chatbot. arXiv, 2024. arXiv:2412.02612. 2024. doi: 10.48550/arXiv.2412.02612Kahn J., Rivière M., Zheng W., Kharitonov E., Xu Q., Mazaré P.-E., et al. Libri-light: A benchmark for ASR with limited or no supervision // Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2020. P. 7669-7673. doi: 10.1109/ICASSP40776.2020.9052942Kahn J., Rivière M., Zheng W., Kharitonov E., Xu Q., Mazaré P.-E., et al. Libri-light: A benchmark for ASR with limited or no supervision. Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 7669–7673. doi: 10.1109/ICASSP40776.2020.9052942Ardila R., Branson M., Davis K., Kohler M., Meyer J., Henretty M., et al. Common Voice: A massively-multilingual speech corpus // Proc. of the 12th Language Resources and Evaluation Conference (LREC). 2020. P. 4218–4222.Ardila R., Branson M., Davis K., Kohler M., Meyer J., Henretty M., et al. Common Voice: A massively-multilingual speech corpus. Proc. of the 12th Language Resources and Evaluation Conference (LREC), 2020, pp. 4218–4222.Pratap V., Xu Q., Sriram A., Synnaeve G., Collobert R. MLS: A largescale multilingual dataset for speech research // Proc. of the Annual Conference of the International Speech Communication Association Interspeech. 2020. P. 2757–2761. doi: 10.21437/Interspeech.2020-2826Pratap V., Xu Q., Sriram A., Synnaeve G., Collobert R. MLS: A largescale multilingual dataset for speech research. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2020, pp. 2757–2761. doi: 10.21437/Interspeech.2020-2826Wang C., Rivière M., Lee A., Wu A., Talnikar C., Haziza D., et al. VoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation // Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021. P. 993–1003. doi: 10.18653/v1/2021.acl-long.80Wang C., Rivière M., Lee A., Wu A., Talnikar C., Haziza D., et al. VoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021, pp. 993–1003. doi: 10.18653/v1/2021.acl-long.80Wang C., Wu A., Gu J., Pino J. CoVoST 2 and massively multilingual speech translation // Proc. of the Annual Conference of the International Speech Communication Association Interspeech. 2021. P. 2247–2251. doi: 10.21437/Interspeech.2021-2027Wang C., Wu A., Gu J., Pino J. CoVoST 2 and massively multilingual speech translation. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2021, pp. 2247-2251. doi: 10.21437/Interspeech.2021-2027Jia Y., Ramanovich M.T., Wang Q., Zen H. CVSS corpus and massively multilingual speech-to-speech translation // Proc. of the 13th Language Resources and Evaluation Conference (LREC). 2022. P. 6691–6703.Jia Y., Ramanovich M.T., Wang Q., Zen H. CVSS corpus and massively multilingual speech-to-speech translation. Proc. of the 13th Language Resources and Evaluation Conference (LREC), 2022, pp. 6691–6703.Di Gangi M.A., Cattoni R., Bentivogli L., Negri M., Turchi M. MuST-C: a multilingual speech translation corpus // Proc. of the 19th Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). 2019. P. 2012–2017. doi: 10.18653/v1/N19-1202Di Gangi M.A., Cattoni R., Bentivogli L., Negri M., Turchi M. MuST-C: a multilingual speech translation corpus. Proc. of the 19th Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019, pp. 2012–2017. doi: 10.18653/v1/N19-1202Conneau A., Ma M., Khanuja S., Zhang Y., Axelrod V., Dalmia S., et al. FLEURS: Few-shot learning evaluation of universal representations of speech // Proc. of the IEEE Spoken Language Technology Workshop (SLT). 2022. P. 798–805. doi: 10.1109/SLT54892.2023.10023141Conneau A., Ma M., Khanuja S., Zhang Y., Axelrod V., Dalmia S., et al. FLEURS: Few-shot learning evaluation of universal representations of speech. Proc. of the IEEE Spoken Language Technology Workshop (SLT), 2022, pp. 798–805. doi: 10.1109/SLT54892.2023.10023141Chen M., Duquenne P.-A., Andrews P., Kao J., Mourachko A., Schwenk H., et al. BLASER: A text-free speech-to-speech translation evaluation metric // Proc. of the 61st Annual Meeting of the Association for Computational Linguistics. 2023. P. 9064–9079. doi: 10.18653/v1/2023.acl-long.504Chen M., Duquenne P.-A., Andrews P., Kao J., Mourachko A., Schwenk H., et al. BLASER: A text-free speech-to-speech translation evaluation metric. Proc. of the 61st Annual Meeting of the Association for Computational Linguistics, 2023, pp. 9064–9079. doi: 10.18653/v1/2023.acl-long.504Saeki T., Xin D., Nakata W., Koriyama T., Takamichi S., Saruwatari H. UTMOS: UTokyo-SaruLab system for VoiceMOS Challenge 2022 // Proc. of the Annual Conference of the International Speech Communication Association Interspeech. 2022. P. 4521–4525. doi: 10.21437/Interspeech.2022-439Saeki T., Xin D., Nakata W., Koriyama T., Takamichi S., Saruwatari H. UTMOS: UTokyo-SaruLab system for VoiceMOS Challenge 2022. Proc. of the Annual Conference of the International Speech Communication Association Interspeech, 2022, pp. 4521-4525. doi: 10.21437/Interspeech.2022-439Kim J., Kong J., Son J. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech // Proc. of the International Conference on Machine Learning. 2021. V. 139. P. 5530–5540.Kim J., Kong J., Son J. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. Proc. of the International Conference on Machine Learning, 2021, vol. 139, pp. 5530–5540.Иванько Д.В., Рюмин Д.А. Автоматический сурдоперевод: обзор нейросетевых методов распознавания и синтеза звучащей и жестовой речи // Научно-технический вестник информационных технологий, механики и оптики. 2024. Т. 24. № 5. С. 669–686. doi: 10.17586/2226-1494-2024-24-5-669-686Ivanko D.V., Ryumin D.A. Automatic sign language translation: a review of neural network methods for recognition and synthesis of spoken and signed language. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2024, vol. 24, no. 5, pp. 669–686. (in Russian). doi: 10.17586/2226-1494-2024-24-5-669-686

The authors declare that there are no conflicts of interest present.