{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T13:22:30Z","timestamp":1787750550536,"version":"build-2784847793"},"reference-count":47,"publisher":"Walter de Gruyter GmbH","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper explores the integration of human linguistic insights into multilingual text-to-speech (TTS) systems by evaluating the Featurally Underspecified Lexicon (FUL) as a theory-driven input representation. Unlike data-intensive end-to end models, FUL offers a compact, interpretable feature set grounded in phonological principles, enabling scalable and equitable TTS development for low-resource languages. We provide a mapping from language-specific phones to FUL feature vectors via a SAMPA intermediate and incorporate these features into a modified FastSpeech architecture. Experiments were conducted to evaluate their ability to generate native, non-native, and code-mixed speech in English and Mandarin. We ran an experiment with a small dataset and one with a larger dataset, which showed that TTS with FUL features as input could produce intelligible native speech with as little as 8\u202fh of training data; with 100\u202fh of training data, intelligible speech could be generated for a language not present in the training data. The approach further supports code-mixed synthesis while preserving consistent timbre and interpretable phonetic control. These results highlight the potential of theory-driven representations for building efficient, scalable, and linguistically informed TTS systems, demonstrating that phonological features can function as both analytical tools and practical inputs for speech technology.<\/jats:p>","DOI":"10.1515\/phon-2025-0072","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T12:55:41Z","timestamp":1787748941000},"source":"Crossref","is-referenced-by-count":0,"title":["Integrating human linguistic insights into AI: theory-driven representation for multilingual text-to-speech"],"prefix":"10.1515","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2561-2113","authenticated-orcid":false,"given":"Cong","family":"Zhang","sequence":"first","affiliation":[{"name":"Speech and Language Sciences , Newcastle University , King George VI Building, Newcastle Upon Tyne , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huinan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Faculty of Linguistics, Philology and Phonetics , University of Oxford , Oxford , UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent , Shenzhen , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiewen","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shengrurenxin Ltd. , Chengdu , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"2026082612553793840_j_phon-2025-0072_ref_001","doi-asserted-by":"crossref","unstructured":"Althaus, Nadja, Aditi Lahiri & Kim Plunkett. 2024. Coronal underspecification as an emerging property in the development of speech processing. Journal of Experimental Psychology: Learning, Memory, and Cognition 50(12). 1932\u20131953. https:\/\/doi.org\/10.1037\/xlm0001367.","DOI":"10.1037\/xlm0001367"},{"key":"2026082612553793840_j_phon-2025-0072_ref_002","doi-asserted-by":"crossref","unstructured":"Arora, Vipul, Aditi Lahiri & Henning Reetz. 2018. Phonological feature-based speech recognition system for pronunciation training in non-native language learning. The Journal of the Acoustical Society of America 143(1). 98\u2013108. https:\/\/doi.org\/10.1121\/1.5017834.","DOI":"10.1121\/1.5017834"},{"key":"2026082612553793840_j_phon-2025-0072_ref_003","doi-asserted-by":"crossref","unstructured":"Bates, Douglas, Martin M\u00e4chler, Ben Bolker & Steve Walker. 2015. Fitting linear mixed-effects models using lme4. Journal of Statistical Software 67(1). 1\u201348. https:\/\/doi.org\/10.18637\/jss.v067.i01.","DOI":"10.18637\/jss.v067.i01"},{"key":"2026082612553793840_j_phon-2025-0072_ref_004","unstructured":"Chomsky, Noam & Morris Halle. 1968. The sound pattern of English. Publisher: ERIC."},{"key":"2026082612553793840_j_phon-2025-0072_ref_005","unstructured":"Christensen, Rune H. B. 2023. Ordinal\u00a0\u2013\u00a0Regression Models for Ordinal Data. R package version 2023.12-4.1. Available at: https:\/\/CRAN.R-project.org\/package=ordinal."},{"key":"2026082612553793840_j_phon-2025-0072_ref_006","unstructured":"Duanmu, San. 2000. The phonology of standard Chinese. Oxford: Oxford University Press."},{"key":"2026082612553793840_j_phon-2025-0072_ref_007","doi-asserted-by":"crossref","unstructured":"Ghini, Mirco. 2012. Place of articulation first. In T. Alan Hall (ed.), Distinctive feature theory, 147\u2013176. De Gruyter Mouton.","DOI":"10.1515\/9783110886672.147"},{"key":"2026082612553793840_j_phon-2025-0072_ref_008","doi-asserted-by":"crossref","unstructured":"Gutkin, Alexander, Martin Jansche & Tatiana Merkulova. 2019. Fonbund: A library for combining cross-lingual phonological segment data. LREC 2018\u00a0\u2013\u00a011th International Conference on Language Resources and Evaluation. ISBN: 9791095546009, 2236\u20132240.","DOI":"10.63317\/448aqn8uvphj"},{"key":"2026082612553793840_j_phon-2025-0072_ref_009","doi-asserted-by":"crossref","unstructured":"Hauser, Ivy. 2023. Differential cue weighting in mandarin sibilant production. Language and Speech 66(4). 1056\u20131090. https:\/\/doi.org\/10.1177\/00238309231152495.","DOI":"10.1177\/00238309231152495"},{"key":"2026082612553793840_j_phon-2025-0072_ref_010","unstructured":"Huang, Ailin, Boyong Wu, Bruce Wang, Chao Yan, Chen Hu, Chengli Feng, Fei Tian, Feiyu Shen, Jingbei Li, Mingrui Chen, et al.. 2025. Step-audio: Unified understanding and generation in intelligent speech interaction. arXiv preprint arXiv:2502.11946."},{"key":"2026082612553793840_j_phon-2025-0072_ref_011","unstructured":"Jakobson, R., G. Fant & M. Halle. 1952. Preliminaries to speech analysis: The distinctive features and their correlates. Technical Report No. 13."},{"key":"2026082612553793840_j_phon-2025-0072_ref_012","doi-asserted-by":"crossref","unstructured":"Kennard, Holly J. & Aditi Lahiri. 2020. Nonesuch phonemes in loanwords. Linguistics 58(1). 83\u2013108. https:\/\/doi.org\/10.1515\/ling-2019-0033.","DOI":"10.1515\/ling-2019-0033"},{"key":"2026082612553793840_j_phon-2025-0072_ref_013","doi-asserted-by":"crossref","unstructured":"Klatt, Dennis H. 1987. Review of text-to-speech conversion for English. The Journal of the Acoustical Society of America 82(3). 737\u2013793. https:\/\/doi.org\/10.1121\/1.395275.","DOI":"10.1121\/1.395275"},{"key":"2026082612553793840_j_phon-2025-0072_ref_014","doi-asserted-by":"crossref","unstructured":"Kotzor, Sandra, Allison Wetterlin & Aditi Lahiri. 2017. Symmetry or asymmetry: Evidence for underspecification in the mental lexicon. In Aditi Lahiri & Sandra Kotzor (eds.), The speech processing lexicon, 85\u2013106. Berlin, Boston: De Gruyter Mouton.","DOI":"10.1515\/9783110422658-005"},{"key":"2026082612553793840_j_phon-2025-0072_ref_015","unstructured":"Kumar, Kundan, Rithesh Kumar, Thibault de Boissiere, Lucas Gestin, Zhen Teoh Wei, Jose Sotelo, Alexandre de Br\u00e9bisson, Yoshua Bengio & Aaron C. Courville. 2019. MelGAN: Generative adversarial networks for conditional waveform synthesis. In Advances in neural information processing systems, vol.\u00a032. Curran Associates, Inc. (3 August, 2023)."},{"key":"2026082612553793840_j_phon-2025-0072_ref_016","doi-asserted-by":"crossref","unstructured":"Lahiri, Aditi. 2018. Predicting universal phonological contrasts. In Larry M. Hyman & Frans Plank (eds.), Phonological typology, 229\u2013272. Berlin, Boston: De Gruyter Mouton.","DOI":"10.1515\/9783110451931-007"},{"key":"2026082612553793840_j_phon-2025-0072_ref_017","doi-asserted-by":"crossref","unstructured":"Lahiri, Aditi & Holly Kennard. 2019. Pertinacity in loanwords: Same underlying systems, different outputs. In Michela Cennamo & Claudia Fabrizio (eds.), Historical linguistics 2015: Selected papers from the 22nd international conference on historical linguistics, naples, 27\u201331 July 2015, vol.\u00a0348 (Current Issues in Linguistic Theory), 57\u201374. Amsterdam: John Benjamins.","DOI":"10.1075\/cilt.348.03lah"},{"key":"2026082612553793840_j_phon-2025-0072_ref_018","doi-asserted-by":"crossref","unstructured":"Lahiri, Aditi & Henning Reetz. 2002. Underspecified recognition. In Carlos Gussenhoven & Natasha Warner (eds.), Laboratory phonology 7, 637\u2013676. Berlin: Mouton de Gruyter.","DOI":"10.1515\/9783110197105.2.637"},{"key":"2026082612553793840_j_phon-2025-0072_ref_019","doi-asserted-by":"crossref","unstructured":"Lahiri, Aditi & Henning Reetz. 2010. Distinctive features: Phonological underspecification in representation and processing. Journal of Phonetics 38(1). 44\u201359. https:\/\/doi.org\/10.1016\/j.wocn.2010.01.002.","DOI":"10.1016\/j.wocn.2010.01.002"},{"key":"2026082612553793840_j_phon-2025-0072_ref_020","doi-asserted-by":"crossref","unstructured":"Lee-Kim, Sang Im. 2014. Revisiting Mandarin \u2018apical vowels\u2019: An articulatory and acoustic study. Journal of the International Phonetic Association 44(3). 261\u2013282. https:\/\/doi.org\/10.1017\/S0025100314000267.","DOI":"10.1017\/S0025100314000267"},{"key":"2026082612553793840_j_phon-2025-0072_ref_021","unstructured":"Lenth, Russell V. 2025. emmeans: Estimated Marginal Means, aka Least-Squares Means. R package version 1.10.7. Available at: https:\/\/CRAN.R-project.org\/package=emmeans."},{"key":"2026082612553793840_j_phon-2025-0072_ref_022","doi-asserted-by":"crossref","unstructured":"Li, Shanpeng & Wentao Gu. 2015. Acoustic analysis of Mandarin affricates. Interspeech 2015. 1680\u20131684. https:\/\/doi.org\/10.21437\/Interspeech.2015-387.","DOI":"10.21437\/Interspeech.2015-387"},{"key":"2026082612553793840_j_phon-2025-0072_ref_023","doi-asserted-by":"crossref","unstructured":"Louw, Johannes Abraham. 2023. Cross-lingual transfer using phonological features for resource-scarce text-to-speech. In 12th speech synthesis workshop (ssw) 2023.","DOI":"10.21437\/SSW.2023-9"},{"key":"2026082612553793840_j_phon-2025-0072_ref_024","doi-asserted-by":"crossref","unstructured":"Maniati, Georgia, Nikolaos Ellinas, Konstantinos Markopoulos, Georgios Vamvoukakis, June Sig Sung, Hyoungmin Park, Aimilios Chalamandaris & Pirros Tsiakoulis. 2021. Cross-lingual low resource speaker adaptation using phonological features. Proceedings of the Annual conference of the International Speech Communication Association, Interspeech 5. 3386\u20133390. ISSN: 19909772. https:\/\/doi.org\/10.21437\/Interspeech.2021-327.","DOI":"10.21437\/Interspeech.2021-327"},{"key":"2026082612553793840_j_phon-2025-0072_ref_025","doi-asserted-by":"crossref","unstructured":"Maniwa, Kazumi, Allard Jongman & Travis Wade. 2009. Acoustic characteristics of clearly spoken English fricatives. The Journal of the Acoustical Society of America 125(6). 3962\u20133973. https:\/\/doi.org\/10.1121\/1.2990715.","DOI":"10.1121\/1.2990715"},{"key":"2026082612553793840_j_phon-2025-0072_ref_026","doi-asserted-by":"crossref","unstructured":"McCulloch, W. S. & W. Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics 5(4). 115\u2013133. https:\/\/doi.org\/10.1007\/bf02478259.","DOI":"10.1007\/BF02478259"},{"key":"2026082612553793840_j_phon-2025-0072_ref_027","unstructured":"N\u00e4slund, Alexander. 2024. Simulating hypernasality with phonological features in Swedish TTS. Bachelor\u2019s Thesis. Swedish title: Simulerad hypernasalitet med fonologiska s\u00e4rdrag i svensk TTS."},{"key":"2026082612553793840_j_phon-2025-0072_ref_028","unstructured":"Povey, Daniel, Arnab Ghoshal, Gilles Boulianne, Lukas Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlicek, Yanmin Qian & Petr Schwarz. 2011. The Kaldi speech recognition toolkit. IEEE 2011 workshop on automatic speech recognition and understanding. Hawaii, USA: IEEE Signal Processing Society."},{"key":"2026082612553793840_j_phon-2025-0072_ref_029","unstructured":"R Core Team. 2024. R: A language and environment for statistical computing. Version 4.4.2. Vienna, Austria: R Foundation for Statistical Computing. Available at: https:\/\/www.R-project.org\/."},{"key":"2026082612553793840_j_phon-2025-0072_ref_030","unstructured":"Ren, Yi, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao & Tie-Yan Liu. 2021. Fastspeech 2: Fast and high-quality end-to-end text to speech. In Iclr."},{"key":"2026082612553793840_j_phon-2025-0072_ref_031","unstructured":"Ren, Yi, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao & Tie Yan Liu. 2019. FastSpeech: Fast, robust and controllable text to speech. Advances in Neural Information Processing Systems 32. arXiv: 1905. 09263."},{"key":"2026082612553793840_j_phon-2025-0072_ref_032","doi-asserted-by":"crossref","unstructured":"Rosenblatt, Frank. 1958. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 65(6). 386\u2013408. https:\/\/doi.org\/10.1037\/h0042519.","DOI":"10.1037\/h0042519"},{"key":"2026082612553793840_j_phon-2025-0072_ref_033","doi-asserted-by":"crossref","unstructured":"Sanchez, Ariadna & Simon King. 2025. Can we reconstruct a dysarthric voice with the large speech model parler tts? Proceedings of Interspeech 2025. 4138\u20134142. https:\/\/doi.org\/10.21437\/Interspeech.2025-2679.","DOI":"10.21437\/Interspeech.2025-2679"},{"key":"2026082612553793840_j_phon-2025-0072_ref_034","doi-asserted-by":"crossref","unstructured":"Shen, Jonathan, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, R. J. Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis & Yonghui Wu. 2018. Natural tts synthesis by conditioning wavenet on mel spectrogram predictions. In ICASSP, 4779\u20134783.","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"2026082612553793840_j_phon-2025-0072_ref_035","doi-asserted-by":"crossref","unstructured":"Staib, Marlene, Huey Teh Tian, Alexandra Torresquintero, Devang S. Ram Mohan, Lorenzo Foglianti, Raphael Lenain & Jiameng Gao. 2020. Phonological features for 0-shot multilingual speech synthesis. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2020-Octob, 2942\u20132946. https:\/\/doi.org\/10.21437\/Interspeech.2020-1821.","DOI":"10.21437\/Interspeech.2020-1821"},{"key":"2026082612553793840_j_phon-2025-0072_ref_036","doi-asserted-by":"crossref","unstructured":"Stoet, Gijsbert. 2010. PsyToolkit: A software package for programming psychological experiments using Linux. Behavior Research Methods 42(4). 1096\u20131104. https:\/\/doi.org\/10.3758\/BRM.42.4.1096.","DOI":"10.3758\/BRM.42.4.1096"},{"key":"2026082612553793840_j_phon-2025-0072_ref_037","doi-asserted-by":"crossref","unstructured":"Stoet, Gijsbert. 2017. PsyToolkit: A novel web-based method for running online questionnaires and reaction-time experiments. Teaching of Psychology 44(1). 24\u201331. https:\/\/doi.org\/10.1177\/0098628316677643.","DOI":"10.1177\/0098628316677643"},{"key":"2026082612553793840_j_phon-2025-0072_ref_038","doi-asserted-by":"crossref","unstructured":"T\u00e5nnander, Christina, Shivam Mehta, Jonas Beskow & Jens Edlund. 2024. Beyond graphemes and phonemes: Continuous phonological features in neural text-to-speech synthesis. 2815\u20132819. Available at: https:\/\/doi.org\/10.21437\/Interspeech.2024-1565.","DOI":"10.21437\/Interspeech.2024-1565"},{"key":"2026082612553793840_j_phon-2025-0072_ref_039","doi-asserted-by":"crossref","unstructured":"Tokuda, Keiichi, Takayoshi Yoshimura, Takashi Masuko, Takao Kobayashi & Tadashi Kitamura. 2000. Speech parameter generation algorithms for hmm-based speech synthesis. ICASSP 3. 1315\u20131318.","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"2026082612553793840_j_phon-2025-0072_ref_040","unstructured":"Wang, Chengyi, Sanyuan Chen, Yu Wu, Ziqiang Zhang, Long Zhou, Shujie Liu, Zhuo Chen, Yanqing Liu, Huaming Wang, Jinyu Li, et al.. 2023. Neural codec language models are zero-shot text to speech synthesizers. arXiv preprint arXiv:2301.02111."},{"key":"2026082612553793840_j_phon-2025-0072_ref_041","doi-asserted-by":"crossref","unstructured":"Wang, Yuxuan, R. J. Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc V. Le, Yannis Agiomyrgiannakis, Rob Clark & Rif A. Saurous. 2017. Tacotron: Towards end-to-end speech synthesis. Interspeech. 4006\u20134010.","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"2026082612553793840_j_phon-2025-0072_ref_042","unstructured":"Wells, John C. 1997. SAMPA computer readable phonetic alphabet. Handbook of Standards and Resources for Spoken Language Systems 4. 684\u2013732."},{"key":"2026082612553793840_j_phon-2025-0072_ref_043","doi-asserted-by":"crossref","unstructured":"Wells, Dan & Korin Richmond. 2021. Cross-lingual transfer of phonological features for low-resource speech synthesis. In 11th ISCA speech synthesis workshop, 160\u2013165. Available at: https:\/\/doi.org\/10.21437\/ssw.2021-28.","DOI":"10.21437\/SSW.2021-28"},{"key":"2026082612553793840_j_phon-2025-0072_ref_044","doi-asserted-by":"crossref","unstructured":"Zen, Heiga, Andrew Senior & Mike Schuster. 2013. Statistical parametric speech synthesis using deep neural networks. In ICASSP, 7962\u20137966.","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"2026082612553793840_j_phon-2025-0072_ref_045","unstructured":"Zhang, Jialu. 2009. Hanyu putonghua jidu yinbiao SAMPA-SC [SAMPA-SC for standard Chinese (putonghua)]. Shengxue Xuebao."},{"key":"2026082612553793840_j_phon-2025-0072_ref_046","unstructured":"Zhang, Cong & Huinan Zeng. 2021. Phonological feature mapping for FeatureTTS. Available at: https:\/\/doi.org\/10.5281\/ZENODO.5553685."},{"key":"2026082612553793840_j_phon-2025-0072_ref_047","doi-asserted-by":"crossref","unstructured":"Zhu, Jian, Cong Zhang & David Jurgens. 2022. Phone-to-audio alignment without text: A semi-supervised approach. ICASSP 2022\u00a0\u2013\u00a02022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8167\u20138171. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746112.","DOI":"10.1109\/ICASSP43922.2022.9746112"}],"container-title":["Phonetica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/phon-2025-0072\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/phon-2025-0072\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T12:55:46Z","timestamp":1787748946000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/phon-2025-0072\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":47,"alternative-id":["10.1515\/phon-2025-0072"],"URL":"https:\/\/doi.org\/10.1515\/phon-2025-0072","relation":{},"ISSN":["0031-8388","1423-0321"],"issn-type":[{"value":"0031-8388","type":"print"},{"value":"1423-0321","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]}}}