Automatic Speech Recognition for Uyghur, Kazakh, and Kyrgyz: An Overview
Source abstract
Abstract
With the emergence of deep learning, the performance of automatic speech recognition (ASR) systems has remarkably improved. Especially for resource-rich languages such as English and Chinese, commercial usage has been made feasible in a wide range of applications. However, most languages are low-resource languages, presenting three main difficulties for the development of ASR systems: (1) the scarcity of the data; (2) the uncertainty in the writing and pronunciation; (3) the individuality of each language. Uyghur, Kazakh, and Kyrgyz as examples are all low-resource languages, involving clear geographical variation in their pronunciation, and each language possesses its own unique acoustic properties and phonological rules. On the other hand, they all belong to the Altaic language family of the Altaic branch, so they share many commonalities. This paper presents an overview of speech recognition techniques developed for Uyghur, Kazakh, and Kyrgyz, with the purposes of (1) highlighting the techniques that are specifically effective for each language and generally effective for all of them and (2) discovering the important factors in promoting the speech recognition research of low-resource languages, by a comparative study of the development path of these three neighboring languages.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Speech Recognition and Synthesis · Speech and Audio Processing · Music and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Center for Speech and Language Technologies, BNRist, Tsinghua University, Beijing 100084, China
School of Information Science and Engineering, Xinjiang University, Ürümqi 830017, China
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
Funding
NSFC
References (100+)
Show source-provided references
1. Automatic speech recognition for under-resourced languages: A survey10.1016/j.specom.2013.07.008 ↗
2. Wu, H. (2011). A Comparative Study on the Phonetics of Turkic Languages, Minzu University of China Press.
3. Yu, D., and Deng, L. (2016). Automatic Speech Recognition, Springer.10.1007/978-1-4471-5779-3 ↗
4. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups10.1109/MSP.2012.2205597 ↗
5. Deng, L., Hinton, G., and Kingsbury, B. (2013, January 26–30). New types of deep neural network learning for speech recognition and related applications: An overview. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada.10.1109/ICASSP.2013.6639344 ↗
6. Abdel-Hamid, O., Mohamed, A.R., Jiang, H., and Penn, G. (2012, January 25–30). Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan.10.1109/ICASSP.2012.6288864 ↗
7. Convolutional neural networks for speech recognition10.1109/TASLP.2014.2339736 ↗
8. Bi, M., Qian, Y., and Yu, K. (2015, January 6–12). Very deep convolutional neural networks for LVCSR. Proceedings of the INTERSPEECH, Dresden, Germany.10.21437/Interspeech.2015-656 ↗
9. Sercu, T., Puhrsch, C., Kingsbury, B., and LeCun, Y. (2016, January 20–25). Very deep multilingual convolutional neural networks for LVCSR. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7472620 ↗
10. Yu, D., Xiong, W., Droppo, J., Stolcke, A., Ye, G., Li, J., and Zweig, G. (2016, January 8–12). Deep convolutional neural networks with layer-wise context expansion and attention. Proceedings of the INTERSPEECH, San Francisc, CA, USA.10.21437/Interspeech.2016-251 ↗
11. Sak, H., Senior, A., and Beaufays, F. (2014). Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv.10.21437/Interspeech.2014-80 ↗
12. Graves, A., Mohamed, A.R., and Hinton, G. (2013, January 26–30). Speech recognition with deep recurrent neural networks. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada.10.1109/ICASSP.2013.6638947 ↗
13. Li, X., and Wu, X. (2015, January 19–24). Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, Australia.10.1109/ICASSP.2015.7178826 ↗
14. Miao, Y., and Metze, F. (2015, January 6–12). On speaker adaptation of long short-term memory recurrent neural networks. Proceedings of the INTERSPEECH, Dresden, Germany.10.21437/Interspeech.2015-290 ↗
15. Miao, Y., Li, J., Wang, Y., Zhang, S.X., and Gong, Y. (2016, January 20–25). Simplifying long short-term memory acoustic models for fast training and decoding. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7472084 ↗
16. Graves, A., Fernández, S., Gomez, F., and Schmidhuber, J. (2006, January 25–29). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, USA.10.1145/1143844.1143891 ↗
17. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv.
18. Chan, W., Jaitly, N., Le, Q., and Vinyals, O. (2016, January 20–25). Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7472621 ↗
19. He, Y., Sainath, T.N., Prabhavalkar, R., McGraw, I., Alvarez, R., Zhao, D., Rybach, D., Kannan, A., Wu, Y., and Pang, R. (2019, January 12–17). Streaming end-to-end speech recognition for mobile devices. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8682336 ↗
20. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, MIT Press.
21. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv.
22. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv.
23. Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., and Salakhutdinov, R. (2019). Transformer-xl: Attentive language models beyond a fixed-length context. arXiv.10.18653/v1/P19-1285 ↗
24. Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., and Soricut, R. (2019). Albert: A lite bert for self-supervised learning of language representations. arXiv.
25. Dong, L., Xu, S., and Xu, B. (2018, January 15–20). Speech-transformer: A no-recurrence sequence-to-sequence model for speech recognition. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8462506 ↗
26. Karita, S., Chen, N., Hayashi, T., Hori, T., Inaguma, H., Jiang, Z., Someki, M., Soplin, N.E.Y., Yamamoto, R., and Wang, X. (2019, January 13–17). A comparative study on Transformer vs RNN in speech applications. Proceedings of the 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Cartagena, Colombia.10.1109/ASRU46091.2019.9003750 ↗
27. Gulati, A., Qin, J., Chiu, C.C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., and Wu, Y. (2020). Conformer: Convolution-augmented transformer for speech recognition. arXiv.10.21437/Interspeech.2020-3015 ↗
28. Schneider, S., Baevski, A., Collobert, R., and Auli, M. (2019). wav2vec: Unsupervised pre-training for speech recognition. arXiv.10.21437/Interspeech.2019-1873 ↗
29. wav2vec 2.0: A framework for self-supervised learning of speech representations
30. Hubert: Self-supervised speech representation learning by masked prediction of hidden units10.1109/TASLP.2021.3122291 ↗
31. Bourlard, H.A., and Morgan, N. (2012). Connectionist Speech Recognition: A Hybrid Approach, Springer Science & Business Media.
32. Rabiner, L., and Juang, B.H. (1993). Fundamentals of Speech Recognition, Prentice-Hall, Inc.
33. Speech recognition using deep neural networks: A systematic review10.1109/ACCESS.2019.2896880 ↗
34. Li, J., Deng, L., Haeb-Umbach, R., and Gong, Y. (2015). Robust Automatic Speech Recognition: A Bridge to Practical Applications, Academic Press.
35. Li, J. (2022). Recent advances in end-to-end automatic speech recognition. APSIPA Trans. Signal Inf. Process., 11.10.1561/116.00000050 ↗
36. Wang, D., Wang, X., and Lv, S. (2019). An overview of end-to-end automatic speech recognition. Symmetry, 11.10.3390/sym11081018 ↗
37. Machine learning in automatic speech recognition: A survey10.1080/02564602.2015.1010611 ↗
38. ASR for under-resourced languages from probabilistic transcription
39. Noisy training for deep neural networks in speech recognition10.1186/s13636-014-0047-0 ↗
40. Data augmentation for deep neural network acoustic modeling
41. Kim, C., Misra, A., Chin, K., Hughes, T., Narayanan, A., Sainath, T., and Bacchiani, M. (2017, January 20–24). Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home. Proceedings of the INTERSPEECH 2017, Stockholm, Sweden.10.21437/Interspeech.2017-1510 ↗
42. Ko, T., Peddinti, V., Povey, D., and Khudanpur, S. (2015, January 6–12). Audio augmentation for speech recognition. Proceedings of the INTERSPEECH, Dresden, Germany.10.21437/Interspeech.2015-711 ↗
43. Jaitly, N., and Hinton, G.E. (2013, January 16). Vocal tract length perturbation (VTLP) improves speech recognition. Proceedings of the ICML Workshop on Deep Learning for Audio, Speech and Language, Atlanta, GA, USA.
44. Laptev, A., Korostik, R., Svischev, A., Andrusenko, A., Medennikov, I., and Rybin, S. (2020, January 17–19). You do not need more data: Improving end-to-end speech recognition by text-to-speech data augmentation. Proceedings of the 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Chengdu, China.10.1109/CISP-BMEI51763.2020.9263564 ↗
45. Li, J., Gadde, R., Ginsburg, B., and Lavrukhin, V. (2018). Training neural speech recognition systems with synthetic speech augmentation. arXiv.
46. Du, C., and Yu, K. (2020, January 4–8). Speaker augmentation for low resource speech recognition. Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9053139 ↗
47. Xu, J., Tan, X., Ren, Y., Qin, T., Li, J., Zhao, S., and Liu, T.Y. (2020, January 6–10). Lrspeech: Extremely low-resource language speech synthesis and recognition. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event, CA, USA.10.1145/3394486.3403331 ↗
48. Park, D.S., Chan, W., Zhang, Y., Chiu, C.C., Zoph, B., Cubuk, E.D., and Le, Q.V. (2019). Specaugment: A simple data augmentation method for automatic speech recognition. arXiv.10.21437/Interspeech.2019-2680 ↗
49. Meng, L., Xu, J., Tan, X., Wang, J., Qin, T., and Xu, B. (2021, January 6–11). MixSpeech: Data augmentation for low-resource automatic speech recognition. Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.10.1109/ICASSP39728.2021.9414483 ↗
50. Nguyen, T.S., Stueker, S., Niehues, J., and Waibel, A. (2020, January 4–8). Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation. Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9054130 ↗
51. Kanda, N., Takeda, R., and Obuchi, Y. (2013, January 8–12). Elastic spectral distortion for low resource speech recognition with deep neural networks. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.10.1109/ASRU.2013.6707748 ↗
52. Ragni, A., Knill, K.M., Rath, S.P., and Gales, M.J. (2014, January 14–18). Data augmentation for low resource languages. Proceedings of the INTERSPEECH. International Speech Communication Association (ISCA), Singapore.10.21437/Interspeech.2014-207 ↗
53. Gokay, R., and Yalcin, H. (2019, January 21–24). Improving low resource Turkish speech recognition with data augmentation and TTS. Proceedings of the 2019 16th International Multi-Conference on Systems, Signals & Devices (SSD), Istanbul, Turkey.10.1109/SSD.2019.8893184 ↗
54. Hartmann, W., Ng, T., Hsiao, R., Tsakalidis, S., and Schwartz, R.M. (2016, January 8–12). Two-stage data augmentation for low-resourced speech recognition. Proceedings of the INTERSPEECH, San Francisc, CA, USA.10.21437/Interspeech.2016-1386 ↗
55. Schultz, T., and Waibel, A. (2001, January 3–7). Experiments on cross-language acoustic modeling. Proceedings of the INTERSPEECH, Aalborg, Denmark.10.21437/Eurospeech.2001-636 ↗
56. Lööf, J., Gollan, C., and Ney, H. (2009, January 6–10). Cross-language bootstrapping for unsupervised acoustic model training: Rapid development of a Polish speech recognition system. Proceedings of the INTERSPEECH, Brighton, UK.10.21437/Interspeech.2009-20 ↗
57. Heigold, G., Vanhoucke, V., Senior, A., Nguyen, P., Ranzato, M., Devin, M., and Dean, J. (2013, January 26–30). Multilingual acoustic models using distributed deep neural networks. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada.10.1109/ICASSP.2013.6639348 ↗
58. Hermansky, H., Ellis, D.P., and Sharma, S. (2000, January 5–9). Tandem connectionist feature extraction for conventional HMM systems. Proceedings of the 2000 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Istanbul, Turkey.
59. Thomas, S., Ganapathy, S., and Hermansky, H. (2010, January 26–30). Cross-lingual and multi-stream posterior features for low resource LVCSR systems. Proceedings of the IINTERSPEECH, Chiba, Japan.10.21437/Interspeech.2010-295 ↗
60. Thomas, S., Ganapathy, S., and Hermansky, H. (2012, January 25–30). Multilingual MLP features for low-resource LVCSR systems. Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan.10.1109/ICASSP.2012.6288862 ↗
61. Knill, K.M., Gales, M.J., Rath, S.P., Woodland, P.C., Zhang, C., and Zhang, S.X. (2013, January 8–12). Investigation of multilingual deep neural networks for spoken term detection. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.10.1109/ASRU.2013.6707719 ↗
62. Veselỳ, K., Karafiát, M., Grézl, F., Janda, M., and Egorova, E. (2012, January 2–5). The language-independent bottleneck features. Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), Miami, FL, USA.10.1109/SLT.2012.6424246 ↗
63. Tüske, Z., Pinto, J., Willett, D., and Schlüter, R. (2013, January 26–30). Investigation on cross-and multilingual MLP features under matched and mismatched acoustical conditions. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, USA.10.1109/ICASSP.2013.6639090 ↗
64. Huang, J.T., Li, J., Yu, D., Deng, L., and Gong, Y. (2013, January 26–30). Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, USA.10.1109/ICASSP.2013.6639081 ↗
65. Ghoshal, A., Swietojanski, P., and Renals, S. (2013, January 26–30). Multilingual training of deep neural networks. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, USA.10.1109/ICASSP.2013.6639084 ↗
66. Dalmia, S., Sanabria, R., Metze, F., and Black, A.W. (2018, January 15–20). Sequence-based multi-lingual low resource speech recognition. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8461802 ↗
67. Inaguma, H., Cho, J., Baskar, M.K., Kawahara, T., and Watanabe, S. (2019, January 12–17). Transfer learning of language-independent end-to-end ASR with language model fusion. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8682918 ↗
68. Watanabe, S., Hori, T., and Hershey, J.R. (2017, January 13–17). Language independent end-to-end architecture for joint language identification and speech recognition. Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Cartagena, Colombia.10.1109/ASRU.2017.8268945 ↗
69. Cho, J., Baskar, M.K., Li, R., Wiesner, M., Mallidi, S.H., Yalta, N., Karafiat, M., Watanabe, S., and Hori, T. (2018, January 18–21). Multilingual sequence-to-sequence speech recognition: Architecture, transfer learning, and language modeling. Proceedings of the 2018 IEEE Spoken Language Technology Workshop (SLT), Athens, Greece.10.1109/SLT.2018.8639655 ↗
70. Zhou, S., Xu, S., and Xu, B. (2018). Multilingual end-to-end speech recognition with a single transformer on low-resource languages. arXiv.
71. Shetty, V.M., and NJ, M.S.M. (2020, January 4–8). Improving the performance of transformer based low resource speech recognition for Indian languages. Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9053808 ↗
72. Müller, M., Stüker, S., and Waibel, A. (2016, January 8–12). Language adaptive DNNs for improved low resource speech recognition. Proceedings of the INTERSPEECH, San Francisco, CA, USA.10.21437/Interspeech.2016-1143 ↗
73. Burget, L., Schwarz, P., Agarwal, M., Akyazi, P., Feng, K., Ghoshal, A., Glembek, O., Goel, N., Karafiát, M., and Povey, D. (2010, January 14–19). Multilingual acoustic modeling for speech recognition based on subspace Gaussian mixture models. Proceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Dallas, TX, USA.10.1109/ICASSP.2010.5495646 ↗
74. Povey, D., Burget, L., Agarwal, M., Akyazi, P., Feng, K., Ghoshal, A., Glembek, O., Goel, N.K., Karafiát, M., and Rastrow, A. (2010, January 14–19). Subspace Gaussian mixture models for speech recognition. Proceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Dallas, TX, USA.10.1109/ICASSP.2010.5495662 ↗
75. Vu, N.T., Imseng, D., Povey, D., Motlicek, P., Schultz, T., and Bourlard, H. (2014, January 4–9). Multilingual deep neural network based acoustic modeling for rapid language adaptation. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy.10.1109/ICASSP.2014.6855086 ↗
76. Tong, S., Garner, P.N., and Bourlard, H. (2017). Multilingual training and cross-lingual adaptation on CTC-based acoustic model. arXiv.10.1016/j.specom.2018.09.001 ↗
77. Tong, S., Garner, P.N., and Bourlard, H. (2019, January 12–17). An investigation of multilingual ASR using end-to-end LF-MMI. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8683338 ↗
78. Kim, S., and Seltzer, M.L. (2018, January 15–20). Towards language-universal end-to-end speech recognition. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8462201 ↗
79. Tong, S., Garner, P.N., and Bourlard, H. (2016, January 2–6). Fast Language Adaptation Using Phonological Information. Proceedings of the INTERSPEECH, Hyderabad, India.
80. Zavaliagkos, G., and Colthurst, T. (1998, January 8–11). Utilizing untranscribed training data to improve performance. Proceedings of the DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, India.10.21437/ICSLP.1998-679 ↗
81. Billa, J. (2021). Improving low-resource ASR performance with untranscribed out-of-domain data. arXiv.
82. Vu, N.T., Kraus, F., and Schultz, T. (2011, January 27–31). Rapid building of an ASR system for under-resourced languages based on multilingual unsupervised training. Proceedings of the Twelfth Annual Conference of the International Speech Communication Association, Florence, Italy.10.21437/Interspeech.2011-787 ↗
83. Renduchintala, A., Ding, S., Wiesner, M., and Watanabe, S. (2018). Multi-modal data augmentation for end-to-end ASR. arXiv.10.21437/Interspeech.2018-2456 ↗
84. Conneau, A., Baevski, A., Collobert, R., Mohamed, A., and Auli, M. (2020). Unsupervised cross-lingual representation learning for speech recognition. arXiv.10.21437/Interspeech.2021-329 ↗
85. Javed, T., Doddapaneni, S., Raman, A., Bhogale, K.S., Ramesh, G., Kunchukuttan, A., Kumar, P., and Khapra, M.M. (March, January 22). Towards building ASR systems for the next billion users. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.
86. Zhang, Z.Q., Song, Y., Wu, M.H., Fang, X., and Dai, L.R. (2021). XLST: Cross-lingual self-training to learn multilingual representation for low resource speech recognition. arXiv.10.1007/s00034-022-02075-7 ↗
87. Wiesner, M. (2021). Automatic Speech Recognition without Transcribed Speech or Pronunciation Lexicons. [Ph.D. Thesis, Johns Hopkins University].
88. Wang, C., Wu, Y., Qian, Y., Kumatani, K., Liu, S., Wei, F., Zeng, M., and Huang, X. (2021, January 22–23). Unispeech: Unified speech representation learning with labeled and unlabeled data. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.
89. Liu, D.R., Chen, K.Y., Lee, H.Y., and Lee, L.S. (2018). Completely unsupervised phoneme recognition by adversarially learning mapping relationships from audio embeddings. arXiv.10.21437/Interspeech.2018-1800 ↗
90. Chen, K.Y., Tsai, C.P., Liu, D.R., Lee, H.Y., and Lee, L.S. (2019). Completely unsupervised speech recognition by a generative adversarial network harmonized with iteratively refined hidden markov models. arXiv.10.21437/Interspeech.2019-2068 ↗
91. Unsupervised speech recognition
92. Liu, A.H., Hsu, W.N., Auli, M., and Baevski, A. (2022). Towards End-to-end Unsupervised Speech Recognition. arXiv.
93. Unsupervised automatic speech recognition: A review10.1016/j.specom.2022.02.005 ↗
94. Adams, O., Wiesner, M., Watanabe, S., and Yarowsky, D. (2019). Massively multilingual adversarial speech recognition. arXiv.10.18653/v1/N19-1009 ↗
95. Black, A.W. (2019, January 12–17). CMU wilderness multilingual speech dataset. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8683536 ↗
96. Pratap, V., Sriram, A., Tomasello, P., Hannun, A., Liptchinsky, V., Synnaeve, G., and Collobert, R. (2020). Massively multilingual ASR: 50 languages, 1 model, 1 billion parameters. arXiv.10.21437/Interspeech.2020-2831 ↗
97. Li, X., Metze, F., Mortensen, D.R., Black, A.W., and Watanabe, S. (2022). ASR2K: Speech recognition for around 2000 languages without audio. arXiv.10.21437/Interspeech.2022-10712 ↗
98. Moran, S., and McCloy, D. (2022, December 25). PHOIBLE 2.0. Jena: Max Planck Institute for the Science of Human History. Available online: https://phoible.org/.
99. Schultz, T. (2002, January 16–20). Globalphone: A multilingual speech and text database developed at Karlsruhe university. Proceedings of the Seventh International Conference on Spoken Language Processing, Denver, CO, USA.10.21437/ICSLP.2002-151 ↗
100. Harper, M.P. (2022, December 25). Data Resources to Support the Babel Program Intelligence Advanced Research Projects Activity (IARPA). Available online: https://www.ldc.upenn.edu/sites/www.ldc.upenn.edu/files/harper.pdf.