Skip to main content

Retrospective and Perspectives of TTS & STT Technology Development and Implementation for South Slavic Under-Resourced Languages

  • Conference paper
  • First Online:
Speech and Computer (SPECOM 2024)

Abstract

Speech technologies such as text-to-speech (TTS) and speech-to-text (STT) are becoming increasingly applicable. Significant improvements in their quality are driven by advancements in deep machine learning. The ability of devices to deeply understand human speech and generate appropriate responses is a hallmark of AI capabilities. Developing speech technology requires extensive speech and language resources, which is why many languages with smaller speaker bases lag behind widely spoken languages in the development of speech technologys. Prior to the deep learning (DL) paradigm, hidden Markov models (HMM) and probabilistic approaches dominated speech technology development. This paper reviews the challenges and solutions in TTS and STT development for Serbian, highlighting the transition from HMM to DL. It also explores the future prospects of speech technology development for under-resourced languages and its role in preserving these languages.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Delić, V., et al.: Speech technology progress based on new machine learning paradigm. Computational Intelligensce and Neuroscience, Wiley, Article 4368036, 19 pages (2019)

    Google Scholar 

  2. Besacier, L., Barnard, E., Karpov, A., Schultz, T.: Automatic speech recognition for under-resourced languages: a survey. Speech Commun. 56, 85–100 (2014)

    Article  Google Scholar 

  3. Swietojanski, P., Ghoshal, A., Renals, S.: Unsupervised crosslingual knowledge transfer in DNN-based LVCSR. In: Workshop SLT, pp. 246–251. IEEE, Miami, FL, USA (2012)

    Google Scholar 

  4. Tan, X., Qin, T., Soong, F., Liu, T.Y.: A Survey on Neural Speech Synthesis. arXiv preprint arXiv:2106.15561 (2021)

  5. Dutoit, T.: High Quality Text-To-Speech Synthesis of the French Language. Ph.D. dissertation. Supervised by Prof. Henri Leich. Faculté Polytechnique de Mons. (1993)

    Google Scholar 

  6. Teranishi R., Umeda N.: Use of pronouncing dictionary in speech synthesis experiments. In: Reports of the Sixth International Congress on Acoustics, vol. 2, pp. 155–158 (1968)

    Google Scholar 

  7. Hallahan, W.I.: DECtalk Software: text-to-speech technology and implementation. Digit. Tech. J. 7(4), 5–19 (1995)

    MATH  Google Scholar 

  8. Dutoit, T.: An Introduction to Text-to-Speech Synthesis. Kluwer Academic Publishers, Dordrecht, Boston, London (1999)

    MATH  Google Scholar 

  9. Van Santen, J.: Assignment of segmental duration in text-to-speech synthesis. Comput. Speech Lang. 8(2), 95–128 (1994)

    Article  MATH  Google Scholar 

  10. Sejnowski, T., Rosenberg, C.R.: Parallel networks that learn to pronounce English text. Complex Syst.1, 145–168 (1987)

    Google Scholar 

  11. McCulloch, N., Bedworth, M., Bridle J.: NETspeak – a re-implementation of NETtalk. Comput. Speech Lang. 2, 289–301 (1987)

    Google Scholar 

  12. Ronanki, S.: Prosody Generation for Text-to-Speech Synthesis. Ph.D. thesis, University of Edinburgh (2019)

    Google Scholar 

  13. Sagisaka, Y., Kaiki, N., Iwahashi, N., Mimura, K.: ATR v-TALK speech synthesis system. In: Proceedings of International Conference on Spoken Language Processing, pp. 483–486 (1992)

    Google Scholar 

  14. Donovan, R.E., Eide, E.: The IBM trainable speech synthesis system. In: Proceedings of 5th International Conference on Spoken Language Processing (ICSLP 98), p. 4, ISCA, Sydney, Australia (1998)

    Google Scholar 

  15. Hunt A.J., Black A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of ICASSP, pp. 373–376. IEEE, Atlanta, GA, USA (1996)

    Google Scholar 

  16. Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura T.: Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis, In: Proceedings of the 6th EUROSPEECH, pp. 2347–2350. Budapest, Hungary (1999)

    Google Scholar 

  17. Yamagishi, J., Kobayashi, T., Nakano, Y., Ogata, K., Isogai J.: Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm. IEEE Trans. Audio Speech Lang. Process. 17(s1), 66–83 (2009)

    Google Scholar 

  18. Yamagishi, J., Onishi, K., Masuko, T., Kobayashi, T.: Modeling of various speaking styles and emotions for HMM-based speech synthesis. In: Proceedings of the 10th EUROSPEECH, pp. 2461–2464. Geneva, Switzerland (2003)

    Google Scholar 

  19. Qian, Y., Liang, H., Soong, F.K.: A cross-language state sharing and mapping approach to bilingual (Mandarin-English) TTS. IEEE Trans. Audio Speech Lang. Process. 17(6), 1231–1239 (2009)

    Article  MATH  Google Scholar 

  20. Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., Oura, K.: Speech synthesis based on hidden markov models. Proc. IEEE 101(5), 1234–1252 (2013)

    Article  Google Scholar 

  21. Yan, Z.-J., Qian, Y., Soong, F.K.: Rich-context unit selection (RUS) approach to high quality TTS. In: Proceedings of ICASSP, pp. 4798–4801. IEEE (2010)

    Google Scholar 

  22. Qian, Y., Soong, F.K., Yan, Z.J.: A unified trajectory tiling approach to high quality speech rendering. IEEE Trans. Audio Speech Lang. Process. 21(2), 280–290 (2013)

    Google Scholar 

  23. Weijters, T., Thole, J.: Speech synthesis with artificial neural networks. In: Proceedings of the IEEE International Conference on Neural Networks, pp. 1764–1769, San Francisco, CA, USA (1993)

    Google Scholar 

  24. Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: Proceedings of the ICASSP, pp. 7962–7966. IEEE (2013)

    Google Scholar 

  25. Fan, Y., Qian, Y., Xie, F.L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Proceedings of 15th INTERSPEECH, pp. 1964–1968. ISCA, Singapore (2014)

    Google Scholar 

  26. Saito, Y., Takamichi, S., Saruwatari, H.: Statistical parametric speech synthesis incorporating generative adversarial networks. IEEE/ACM Trans. Audio Speech Lang. Process. 26(1), 84–96 (2018)

    Article  Google Scholar 

  27. Wu, Z., King, S.: Improving trajectory modelling for DNN-based speech synthesis by using stacked bottleneck features and minimum generation error training. IEEE/ACM Trans. Audio Speech Lang. Process. 24(7), 1255–1265 (2016)

    Article  MATH  Google Scholar 

  28. Fan, Y., Qian, Y., Soong, F.K., He, L.: Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis. In: Proceedings of ICASSP, pp. 4475–4479. IEEE (2015)

    Google Scholar 

  29. Wu, Z., Swietojanski, P., Veaux, C., Renals, S., King, S.: A study of speaker adaptation for DNN-based speech synthesis. In: Proceedings of the 16th INTERSPEECH, pp. 879–883, Dresden (2015)

    Google Scholar 

  30. Hojo, N., Ijima, Y., Mizuno, H.: An investigation of DNN-based speech synthesis using speaker codes. In: Proceedings of the 17th INTERSPEECH 2016, pp. 2278–2282. San Francisco, USA (2016)

    Google Scholar 

  31. Fan, Y., Qian, Y., Soong, F.K., He, L.: Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis. In: Proceedings of ICASSP, pp. 4475–4479. Brisbane, Australia (2015)

    Google Scholar 

  32. Brave, S., Nass, C.: Emotion in human-computer interaction. In: Sears, A., Jacko, J.A. (eds.) Human-Computer Interaction Fundamentals, pp. 53–68, CRC, Boca Raton, USA (2009)

    Google Scholar 

  33. Yamagishi, J., Onishi, K., Masuko, T., Kobayashi, T.: Modeling of various speaking styles and emotions for HMM-based speech synthesis. In: 8th EUROSPEECH, Geneva, Switzerland (2003)

    Google Scholar 

  34. Eyben, F., et al.: Unsupervised clustering of emotion and voice styles for expressive TTS. In: Proceedings of ICASSP, pp. 4009–4012. IEEE (2012)

    Google Scholar 

  35. Aihara, R., Takashima, R., Takiguchi, T., Ariki, Y.: GMM-based emotional voice conversion using spectrum and prosody features. Am. J. Signal Process. 2(5), 134–138 (2012)

    Article  MATH  Google Scholar 

  36. Lorenzo-Trueba, J., Henter, G.E., Takaki, S., Yamagishi, J., Morino, Y., Ochiai, Y.: Investigating different representations for modeling and controlling multiple emotions in DNN-based speech synthesis. Speech Commun. 99, 135–143 (2018)

    Article  Google Scholar 

  37. Luo, Z., Chen, J., Takiguchi, T., Ariki, Y.: Emotional voice conversion with adaptive scales F0 based on wavelet transform using limited amount of emotional data. In: Proceedings of the 18th INTERSPEECH, pp. 3399–3403. ISCA (2017)

    Google Scholar 

  38. Ming, H., Huang, D., Xie, L., Wu, J., Dong, M., Li, H.: Deep bidirectional LSTM modeling of timbre and prosody for emotional voice conversion. In: Proceedings of the 17th INTERSPEECH 2016, pp. 2453–2457. ISCA (2016)

    Google Scholar 

  39. An, S., Ling, Z., Dai, L.: Emotional statistical parametric speech synthesis using LSTM-RNNS. In: Asia-Pacific Signal and Information Processing Association Annual Samit and Conference (APSIPA ASC), pp. 1613–1616, IEEE (2017)

    Google Scholar 

  40. Skerry-Ryan, R., et al.: Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron. In: Proceedings of the 34th International Conference on Machine Learning, pp. 4693–4702. PMLR (2018)

    Google Scholar 

  41. Wu, P., Ling, Z., Liu, L., Jiang, Y., Wu, H., Dai, L.: End-to-end emotional speech synthesis using style tokens and semisupervised training. In: Asia-Pacific Signal and Information Processing Association Annual Samit and Conf. (APSIPA ASC), pp. 623–627. IEEE (2019)

    Google Scholar 

  42. Zhou, K., Sisman, B., Rana, R., Schuller, B.W., Li, H.: Speech synthesis with mixed emotions. IEEE Trans. Affect. Comput. 14(4), 3120–3134 (2022)

    Article  MATH  Google Scholar 

  43. Van den Oord, A., Dieleman, S., Zen, H., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 12 (2016)

  44. Van den Oord, A., et al.: Parallel WaveNet: fast high- fidelity speech synthesis. In: Proceedings of the 35th International Conference on Machine Learning, pp. 3915–3923. Stockholm, Sweden (2018)

    Google Scholar 

  45. Arik, S.O., et al.: Deep voice: real-time neural text-to-speech. In: Proceedings of the 34th International Conference on Machine Learning, pp. 195–204. PMLR, Sydney, Australia (2017)

    Google Scholar 

  46. Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. In: Proceedings of the 18th INTERSPEECH 2017, pp. 4006–4010. ISCA, Stockholm, Sweden (2017)

    Google Scholar 

  47. Shen, J., et al.: Natural TTS synthesis by conditioning WaveNet on MEL spectrogram predictions. In: Proceedings of ICASSP, pp. 4779–4783. Calgary, Canada (2018)

    Google Scholar 

  48. Ping, W., Peng, K., Gibiansky, A., et al.: Deep voice 3: scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654 (2017)

  49. Arik, S.Ö, Chen, J., Peng, K., Ping, W., Zhou, Y.: Neural voice cloning with a few samples. In: Advances in Neural Information Processing Systems 31, 32nd Conference on Neural Information Processing Systems, pp. 10040–10050, Montreal, Canada (2018)

    Google Scholar 

  50. Nachmani, E., Polyak, A., Taigman, Y., Wolf, L.: Fitting new speakers based on a short untranscribed sample. In: Proceedings of the 35th International Conference on Machine Learning, pp. 3680–3688. Stockholm, Sweden (2018)

    Google Scholar 

  51. Akuzawa, K., Iwasawa, Y., Matsuo, Y.: Expressive speech synthesis via modeling expressions with variational autoencoder. In: Proceedings of the 19th INTERSPEECH, pp. 3067–3071. ISCA, Hyderabad, India (2018)

    Google Scholar 

  52. Ren, Y., et al.: Fastspeech: fast, robust and controllable text to speech. Adv. Neural Inf. Process. systems 32 (2019)

    Google Scholar 

  53. Ren, Y., et al.: Fastspeech 2: Fast and high-quality end-to-end text to speech. Preprint arXiv:2006.04558 (2020)

  54. Nosek, T., Suzić, S., Sečujski, M., Stanojev, V., Pekar, D., Delić, V.: End-to-end speech synthesis for the Serbian language based on Tacotron. In: Karpov, A. Delić, V., (eds.) SPECOM 2024, LNAI Part I - 15299, Springer, Heidelberg, Belgrade, Serbia (2024)

    Google Scholar 

  55. Wang, C., et al.: Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers. arXiv preprint arXiv:2301.02111 (2023)

  56. Zhang, Z., et al.: Speak foreign languages with your own voice: Cross-lingual neural codec language modeling. arXiv preprint arXiv:2303.03926 (2023)

  57. Han, B., et al.: VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment. arXiv preprint arXiv:2406.07855 (2024)

  58. Meng, L., et al.: Autoregressive Speech Synthesis without Vector Quantization. arXiv preprint arXiv:2407.08551 (2024)

  59. Casanova, E., Weber, J., Shulby, C., Candido Junior, A., Gölge, E., Antonelli Ponti, M.: YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone. arXiv preprint arXiv:2112.02418 (2024)

  60. Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. arXiv preprint arXiv:2010.05646 (2020)

  61. Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: A Flow-based Generative Network for Speech Synthesis. arXiv preprint arXiv:1811.00002 (2018)

  62. Casanova, E., et al.: XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model. arXiv preprint arXiv:2406.04904 (2024)

  63. Sečujski, M., Obradović, R., Pekar, D., Jovanov, Lj., Delić, V.: AlfaNum system for speech synthesis in Serbian language. In: Proceedings of the 5th International Conference Text, Speech and Dialogue (TSD 2002), pp. 237–244. Brno, Czech Republic (2002)

    Google Scholar 

  64. Pakoci, E., Mak, R.: HMM-based speech synthesis for the Serbian language. In: Proceedings of the 56th ETRAN, vol. TE4, pp. 1–4. Zlatibor, Serbia (2012)

    Google Scholar 

  65. Delić, T., Sečujski, M., Suzić, S.: A review of serbian parametric speech synthesis based on deep neural networks. TELFOR J. 9(1), 32–37 (2017)

    Article  Google Scholar 

  66. Sečujski, M., Pekar, D., Suzić, S., Smirnov, A., Nosek, T.: Speaker/style-dependent neural network speech synthesis based on speaker/style embedding. J. Univ. Comput. Sci. 26(4), 434–453 (2020)

    Google Scholar 

  67. Suzić, S., Sečujski, M., Nosek, T., Delić, V., Pekar, D.: HiFi-GAN based text-to-speech synthesis in Serbian. In: Proceedings of 30th EUSIPCO, pp. 2231–2235, Belgrade, Serbia (2022)

    Google Scholar 

  68. Sakai, T., Doshita, S.: Phonetic Typewriter. J. Acoust. Soc. Am. 33, 1664 (1961)

    Article  Google Scholar 

  69. Davis, K.H., Biddulph, R., Balashek, S.: Automatic recognition of spoken digits. J. Acoust. Soc. Am. 24, 637–642 (1952)

    Article  Google Scholar 

  70. Vintsyuk, T.K.: Speech discrimination by dynamic programming. Cybern. Syst. Anal. 4, 52–57 (1972)

    Article  MATH  Google Scholar 

  71. Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Process. 26, 43–49 (1978)

    Article  MATH  Google Scholar 

  72. Atal, B.S., Hanauer, S.L.: Speech analysis and synthesis by linear prediction of the speech wave. J. Acoust. Soc. Am. 50, 637–655 (1971)

    Article  MATH  Google Scholar 

  73. Jelinek, F., Bahl, L., Mercer, R.: Design of a linguistic statistical decoder for the recognition of continuous speech. IEEE Trans. Inf. Theory 21, 250–256 (1975)

    Article  MATH  Google Scholar 

  74. Klatt, D.H.: Review of the ARPA speech understanding project. J. Acoust. Soc. Am. 62, 1345–1366 (1977)

    Article  MATH  Google Scholar 

  75. Jelinek, F.: Continuous speech recognition by statistical methods. Proc. IEEE 64, 532–556 (1976)

    Article  MATH  Google Scholar 

  76. Levinson, S.E., Rabiner, L.R., Sondhi, M.M.: An Introduction to the application of the theory of probabilistic functions of a markov process to automatic speech recognition. Bell Syst. Tech. J. 62, 1035–1074 (1983)

    Article  MathSciNet  MATH  Google Scholar 

  77. Juang, B.-H.: Maximum-likelihood estimation for mixture multivariate stochastic observations of markov chains. AT&T Tech. J. 64, 1235–1249 (1985)

    Article  MathSciNet  MATH  Google Scholar 

  78. Juang, B.-H., Levinson, S., Sondhi, M.: Maximum likelihood estimation for multivariate mixture observations of Markov chains. IEEE Trans. on Inform. Theory 32, 307–309 (1986)

    Article  MATH  Google Scholar 

  79. Lee, K.-F.: Context-independent phonetic hidden Markov models for speaker-independent continuous speech recognition. IEEE Trans. Acoust. Speech Signal Process. 38, 599–609 (1990)

    Article  MATH  Google Scholar 

  80. Young, S.J., Woodland, P.C.: State clustering in hidden Markov model-based continuous speech recognition. Comput. Speech Lang. 8, 369–383 (1994)

    Article  MATH  Google Scholar 

  81. Mermelstein, P.: Distance measures for speech recognition, psychological and instrumental. Pattern Recogn. Artif. Intell. 374–388 (1976)

    Google Scholar 

  82. Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87, 1738–1752 (1990)

    Article  MATH  Google Scholar 

  83. Viikki, O., Laurila, K.: Cepstral domain segmental feature vector normalization for noise robust speech recognition. Speech Commun. 25, 133–147 (1998)

    Article  MATH  Google Scholar 

  84. Prasad, N.V., Umesh, S.: Improved cepstral mean and variance normalization using Bayesian framework. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 156–161. IEEE, Olomouc, Czech Republic (2013)

    Google Scholar 

  85. Rehr, R., Gerkmann, T.: Cepstral noise subtraction for robust automatic speech recognition. In: Proceedings of ICASSP, pp. 375–378. IEEE, South Brisbane, Queensland, Australia (2015)

    Google Scholar 

  86. Hermansky, H., Morgan, N.: RASTA processing of speech. IEEE Trans. on Speech Audio Processing 2, 578–589 (1994)

    Article  MATH  Google Scholar 

  87. Bahl, L., Brown, P., De Souza, P., Mercer, R.: Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In: Proceedings of ICASSP, pp. 49–52. IEEE, Tokyo, Japan (1986)

    Google Scholar 

  88. Valtchev, V., Odell, J.J., Woodland, P.C., Young, S.J.: MMIE training of large vocabulary recognition systems. Speech Commun. 22, 303–314 (1997)

    Article  Google Scholar 

  89. Juang, B.-H., Hou, W., Lee, C.-H.: Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5, 257–265 (1997)

    Article  MATH  Google Scholar 

  90. Povey, D., Woodland, P.C.: Minimum phone error and i-smoothing for improved discriminative training. In: Proceedings of ICASSP, pp. I-105-I–108. IEEE, Orlando, FL, USA (2002)

    Google Scholar 

  91. Ng, A.Y., Jordan, M.I.: On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes. In: Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, pp. 841–848. MIT Press, Cambridge, MA, USA (2001)

    Google Scholar 

  92. Macherey, W.: Discriminative training and acoustic modeling for automatic speech recognition. Ph.D. Thesis, Aachen Techn. Hochsch (2010)

    Google Scholar 

  93. Baker, J.: The DRAGON system–An overview. IEEE Trans. Acoust. Speech Signal Process. 23, 24–29 (1975)

    Article  MATH  Google Scholar 

  94. Bahl, L.R., Jelinek, F., Mercer, R.L.: A maximum likelihood approach to continuous speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5, 179–190 (1983)

    Google Scholar 

  95. Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Comput. Speech Lang. 13, 359–393 (1999)

    Article  MATH  Google Scholar 

  96. Goodman, J.T.: A bit of progress in language modeling. Comput. Speech Lang. 15, 403–434 (2001)

    Article  MATH  Google Scholar 

  97. Lippmann, R.P.: Review of neural networks for speech recognition. Neural Comput. 1, 1–38 (1989)

    Article  MATH  Google Scholar 

  98. Bourlard, H.A., Morgan, N.: Connectionist Speech Recognition: a Hybrid Approach. Springer, US, Boston, MA (1994)

    Book  MATH  Google Scholar 

  99. Mohamed, A., Dahl, G.E., Hinton, G.E.: Deep belief networks for phone recognition. In: NIPS Workshop on Deep Learning for Speech Recognition and Related Applications, pp. 1–9. Vancouver, BC, Canada (2009)

    Google Scholar 

  100. Dahl, G.E., Dong Yu, Li Deng, Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio, Speech, Lang. Process. 20, 30–42 (2012)

    Google Scholar 

  101. Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning, pp. 369–376. ACM Press, Pittsburgh, Pennsylvania (2006)

    Google Scholar 

  102. Maas, A., Xie, Z., Jurafsky, D., Ng, A.: Lexicon-free conversational speech recognition with neural networks. In: Proceedings Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 345–354. Denver, Colorado (2015)

    Google Scholar 

  103. Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., Bengio, Y.: End-to-end attention-based large vocabulary speech recognition. In: Proceedings of ICASSP, pp. 4945–4949. Shanghai (2016)

    Google Scholar 

  104. Karita, S., et al.: A comparative study on transformer vs RNN in speech applications. In: Automatic speech recognition and understanding workshop (ASRU), pp. 449–456. IEEE, SG, Singapore (2019)

    Google Scholar 

  105. Zhu, H., Wang, L., Cheng, G., Wang, J., Zhang, P., Yan, Y.: Wav2vec-S: semi-supervised pre-training for low-resource ASR. In: Proceedings of the 23th INTERSPEECH, pp. 4870–4874. ISCA (2022)

    Google Scholar 

  106. Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: Unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)

  107. Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the International Conference on Machine Learning, pp. 28492–28518 (2023)

    Google Scholar 

  108. Suzić, S., Ostrogonac, S., Pakoci, E., Bojanić, M.: Building a speech repository for a Serbian LVCSR system. Telfor J. 6(2), 109–114 (2014)

    Article  Google Scholar 

  109. Nosek, T., Suzić, S., Delić, V., Sečujski, M.: Cross-lingual text-to-speech with prosody embedding. In: Proceedings of IWSSIP, 5 pages (2023)

    Google Scholar 

  110. Pakoci, E.T., Popović, B.Z.: Recurrent neural networks and morphological features in language modeling for Serbian. In: 29th Telecommunication Forum (TELFOR), 8 pages. IEEE (2021)

    Google Scholar 

  111. Delić, V., Sečujski, M., Sedlar, N.V., Mišković, D., Mak, R., Bojanić, M.: How speech technologies can help people with disabilities. In: Ronzhin, A., Potapova, R., Delić, V. (eds.) 16th SPECOM 2014, LNAI, vol. 8773, pp. 243–250. Springer. Novi Sad, Serbia (2014)

    Google Scholar 

  112. Delić, V., et al.: Central audio-library of the university of Novi Sad. In: Proceedings of the Intelligent Distributed Computing XIII, pp. 467–476. Springer International Publishing (2020)

    Google Scholar 

  113. Pakoci, E., Pekar, D., Popović, B., Sečujski, M., Delić, V.: Overcoming data sparsity in automatic transcription of dictated medical findings. In: Proceedings of the 30th EUSIPCO, pp. 454–458. IEEE (2022)

    Google Scholar 

  114. Popović, B., Pakoci, E., Jakovljević, N., Kočiš, G., Pekar, D.: Voice assistant application for the Serbian language. In: 23rd Telecommunication Forum (TELFOR), pp. 858–861. IEEE (2015)

    Google Scholar 

  115. Reitmaier, T., et al: Opportunities and challenges of automatic speech recognition systems for low-resource language speakers. In Proceedings of the CHI Conference on Human Factors in Computing Systems, p. 17 (2022)

    Google Scholar 

  116. Mu, Z., Yang, X., Dong, Y.: Review of end-to-end speech synthesis technology based on deep learning. arXiv preprint arXiv:2104.09995 (2021)

  117. Ogayo, P., Neubig, G., Black, A.W.: Building TTS systems for low resource languages under resource constraints. In: Proceedings Speech for Social Good Workshop, p. 5 (2022)

    Google Scholar 

  118. Jimerson, R., Liu, Z., Prud’Hommeaux, E.: An (unhelpful) guide to selecting the best ASR architecture for your under-resourced language. In: Proceedings of the 61st Annual Meeting of the Association for Comp. Linguistics (Vol. 2 Short Papers), pp. 1008–1016 (2023)

    Google Scholar 

  119. Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449–12460 (2020)

    Google Scholar 

  120. Popović, B.Z., Pakoci, E.T., Pekar, D.J.: Transfer learning for domain and environment adaptation in Serbian ASR. Telfor Journal 12(2), 110–115 (2020)

    Article  MATH  Google Scholar 

  121. Delić, V.D., Pekar, D.J., Sečujski, M.S., Popović, B.Z., Pakoci, E.T., Suzić, S.B.: Development of speech technology for Serbian and its applications. In: Proceedings of the First Serbian International Conference on Applied Artificial Intelligence, p. 7. Kragujevac, Serbia (2022)

    Google Scholar 

Download references

Acknowledgments

This research was supported by the Science Fund of the Republic of Serbia, Grant No. 7449, Multimodal multilingual human-machine speech communication, AI-SPEAK, and by the Ministry of Science, Technological Development and Innovation (Contract No. 451–03-65/2024–03/200156) and the Faculty of Technical Sciences, University of Novi Sad through project “Scientific and Artistic Research Work of Researchers in Teaching and Associate Positions at the Faculty of Technical Sciences, University of Novi Sad” (No. 01–3394/1).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Milan Sečujski .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Sečujski, M. et al. (2025). Retrospective and Perspectives of TTS & STT Technology Development and Implementation for South Slavic Under-Resourced Languages. In: Karpov, A., Delić, V. (eds) Speech and Computer. SPECOM 2024. Lecture Notes in Computer Science(), vol 15299. Springer, Cham. https://doi.org/10.1007/978-3-031-77961-9_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-77961-9_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-77960-2

  • Online ISBN: 978-3-031-77961-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics