{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:28:59Z","timestamp":1781670539973,"version":"3.54.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Iran J Comput Sci"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s42044-024-00212-w","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T14:25:16Z","timestamp":1731594316000},"page":"125-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Parallel convolutional neural network and hybrid architectures for accented speech recognition in Malayalam"],"prefix":"10.1007","volume":"8","author":[{"given":"Rizwana Kallooravi","family":"Thandil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V. K.","family":"Muneer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B.","family":"Premjith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"212_CR1","doi-asserted-by":"publisher","unstructured":"Aks\u00ebnova, A., Chen, Z., Chiu, C., Daan, V. E., Golik, P., Han, W., King, L., Ramabhadran, B., Rosenberg, A., Schwartz, S., Wang, G.: Accented Speech Recognition: benchmarking, pre-training, and diverse data. Cornell University (2022). https:\/\/doi.org\/10.48550\/arxiv.2205.08014","DOI":"10.48550\/arxiv.2205.08014"},{"key":"212_CR2","doi-asserted-by":"crossref","unstructured":"Das, N., Bodapati, S., Sunkara, M., Srinivasan, S., Chau, D.H.: Best of both worlds: robust accented speech recognition with adversarial transfer learning, Interspeech 2021 (2021). https:\/\/www.amazon.science\/publications\/best-of-both-worlds-robust-accented-speech-recognition-with-adversarial-transfer_learning","DOI":"10.21437\/Interspeech.2021-1888"},{"issue":"Article ID 6825","key":"212_CR3","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1155\/2022\/6825555","volume":"2022","author":"MA Hassan","year":"2022","unstructured":"Hassan, M.A., Rehmat, A., Khan, M.U.G., Yousaf, M.H.: Improvement in automatic speech recognition of South Asian accent using transfer learning of DeepSpeech2. Math. Probl. Eng. 2022(Article ID 6825555), 12 (2022). https:\/\/doi.org\/10.1155\/2022\/6825555","journal-title":"Math. Probl. Eng."},{"key":"212_CR4","doi-asserted-by":"crossref","unstructured":"Ni,J., Wang, L., Gao, H., et al.: Unsupervised text-to-speech synthesis by unsupervised automatic speech recognition (2022). arXiv:2203.15796","DOI":"10.21437\/Interspeech.2022-816"},{"key":"212_CR5","doi-asserted-by":"crossref","unstructured":"Jain,A., Singh, V.P., Rath, S.P.: A multi-accent acoustic model using a mixture of experts for speech recognition. In: Proc. Interspeech, pp. 779\u2013783 (2019)","DOI":"10.21437\/Interspeech.2019-1667"},{"key":"212_CR6","doi-asserted-by":"crossref","unstructured":"Qian, Y., Gong, X., Huang, H.: IEEE\/ACM Transactions on Audio, Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition Speech, and Language Processing, vol. 30, pp. 2842\u20132853","DOI":"10.1109\/TASLP.2022.3198546"},{"key":"212_CR7","volume-title":"End-to-end Japanese Multi-dialect Speech Recognition and Dialect Identification with Multi-task Learning","author":"R Imaizumi","year":"2020","unstructured":"Imaizumi, R., Masumura, R., Shiota, S., Kiya, H.: End-to-end Japanese Multi-dialect Speech Recognition and Dialect Identification with Multi-task Learning. NTT Media Intelligence Laboratories, NTT Corporation, Tokyo (2020)"},{"key":"212_CR8","doi-asserted-by":"publisher","unstructured":"Deng, K., Cao, S., Ma, L.: Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning (2021). https:\/\/doi.org\/10.48550\/arXiv.2109.07349. arXiv:2109.07349","DOI":"10.48550\/arXiv.2109.07349"},{"key":"212_CR9","doi-asserted-by":"publisher","unstructured":"Huang,H., Xiang, X., Yang, Y., Ma, R., Qian, Y.: AISpeech-SJTU accent identification system for the accented English speech recognition challenge. In: ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6254\u20136258. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414292","DOI":"10.1109\/ICASSP39728.2021.9414292"},{"issue":"18","key":"212_CR10","doi-asserted-by":"publisher","first-page":"8412","DOI":"10.3390\/app11188412","volume":"11","author":"H-J Na","year":"2021","unstructured":"Na, H.-J., Park, J.-S.: Accented speech recognition based on end-to-end domain adversarial training of neural networks. Appl. Sci. 11(18), 8412 (2021). https:\/\/doi.org\/10.3390\/app11188412","journal-title":"Appl. Sci."},{"key":"212_CR11","doi-asserted-by":"publisher","first-page":"23367","DOI":"10.1007\/s11042-023-16438-y","volume":"83","author":"AS Dhanjal","year":"2023","unstructured":"Dhanjal, A.S., Singh, W.: A comprehensive survey on automatic speech recognition using neural networks. Multimed. Tools Appl. 83, 23367\u201323412 (2023)","journal-title":"Multimed. Tools Appl."},{"key":"212_CR12","doi-asserted-by":"publisher","unstructured":"Chen, Y.-C., Yang, Z., Yeh, C.-F., Jain, M., Seltzer, M.L.: Aipnet: generative adversarial pre-training of accent-invariant networks for end-to-end speech recognition. In: ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 6979\u20136983 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053098","DOI":"10.1109\/ICASSP40776.2020.9053098"},{"key":"212_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., Ouyang, B., Liao, D., Xia, S., Li, L., Hong, Q.: End-to-end multi-accent speech recognition with unsupervised accent modelling. In: ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021)","DOI":"10.1109\/ICASSP39728.2021.9414833"},{"key":"212_CR14","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Abdel-Rahman, M., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional Neural Networks for Speech Recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. (2014)","DOI":"10.21437\/Interspeech.2013-455"},{"key":"212_CR15","unstructured":"Sasikuttan, A., James, A., Mathews, A.P., Abhishek, M.P., Sebastian, K.: Malayalam speech to text conversion. Int. Res. J. Eng. Technol. (IRJET) (2020)"},{"key":"212_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894","volume":"59","author":"D Issa","year":"2020","unstructured":"Issa, D., Fatih Demirci, M., Yazici, A.: Speech emotion recognition with deep convolutional neural networks. Biomed. Signal Process. Control 59, 101894 (2020)","journal-title":"Biomed. Signal Process. Control"},{"key":"212_CR17","doi-asserted-by":"crossref","unstructured":"Passricha, V., Kumar Aggarwal, R.: Convolutional neural networks for raw speech recognition. From Natural to Artificial Intelligence Algorithms and Applications(2018)","DOI":"10.5772\/intechopen.80026"},{"key":"212_CR18","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Beaufays, F.: Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling (2014)","DOI":"10.21437\/Interspeech.2014-80"},{"key":"212_CR19","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1007\/s11265-017-1291-1","volume":"90","author":"J Yi","year":"2018","unstructured":"Yi, J., Wen, Z., Tao, J., et al.: CTC regularized model adaptation for improving LSTM RNN based multi-accent mandarin speech recognition. J Sign Process Syst 90, 985\u2013997 (2018)","journal-title":"J Sign Process Syst"},{"issue":"5","key":"212_CR20","first-page":"4296","volume":"6","author":"KR Ghule","year":"2015","unstructured":"Ghule, K.R., Deshmukh, R.R.: Automatic speech recognition of marathi isolated words using neural network. Int. J. Comput. Sci. Inf. Technol. (IJCSIT) 6(5), 4296\u20134298 (2015)","journal-title":"Int. J. Comput. Sci. Inf. Technol. (IJCSIT)"},{"issue":"2","key":"212_CR21","first-page":"81","volume":"4","author":"S Thereses","year":"2014","unstructured":"Thereses, S., Lingam, C.: Isolated word speech recognition system using Htk. Int. J. Comput. Sci. Eng. Inf. Technol. Res. (IJCSEITR) 4(2), 81\u201386 (2014)","journal-title":"Int. J. Comput. Sci. Eng. Inf. Technol. Res. (IJCSEITR)"},{"key":"212_CR22","doi-asserted-by":"publisher","first-page":"9969","DOI":"10.1007\/s11042-022-12304-5","volume":"81","author":"Y Dokuz","year":"2022","unstructured":"Dokuz, Y., T\u00fcfekci, Z.: Feature-based hybrid strategies for gradient descent optimization in end-to-end speech recognition. Multimed. Tools Appl. 81, 9969\u20139988 (2022). https:\/\/doi.org\/10.1007\/s11042-022-12304-5","journal-title":"Multimed. Tools Appl."},{"issue":"1","key":"212_CR23","first-page":"34","volume":"14","author":"U Nallasamy","year":"2006","unstructured":"Nallasamy, U., Venkataraman, S.: Phonetic recognition of malayalam speech using MFCC and LPC features. IEEE Trans. Audio Speech Lang. Process. 14(1), 34\u201341 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"212_CR24","unstructured":"Chakravarthy, S., Sitaram, S.: Accent-agnostic speech recognition for Malayalam using deep learning. In: Proceedings of the International Conference on Signal Processing and Communications, pp. 205\u2013210 (2020)"},{"issue":"8","key":"212_CR25","first-page":"2470","volume":"30","author":"S Sitaram","year":"2019","unstructured":"Sitaram, S., Rao, K., Shankar, V.: Adversarial training for accented speech recognition in Malayalam. IEEE Trans. Neural Netw. Learn. Syst. 30(8), 2470\u20132479 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"212_CR26","unstructured":"Balaji, K., Ramakrishnan, A.G., Chinnappa, S.: Multi-task learning for accented speech recognition in Malayalam. In: Proceedings of the international conference on computational linguistics, pp. 450\u2013460 (2020)"},{"key":"212_CR27","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)"},{"key":"212_CR28","unstructured":"Jain, A., Venkatesh, Y.: Data augmentation techniques for robust Malayalam ASR. In: Proceedings of the international conference on natural language processing, pp. 78\u201388 (2021)"},{"key":"212_CR29","doi-asserted-by":"publisher","unstructured":"Mehra, S., Susan, S.: Early fusion of phone embeddings for recognition of low-resourced accented speech. In: 4th International Conference on Artificial Intelligence and Speech Technology (AIST), Delhi, pp. 1\u20135 (2022). https:\/\/doi.org\/10.1109\/AIST55798.2022.10064735","DOI":"10.1109\/AIST55798.2022.10064735"},{"issue":"1","key":"212_CR30","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10772-020-09757-0","volume":"25","author":"A Kumar","year":"2022","unstructured":"Kumar, A., Aggarwal, R.K.: Hindi speech recognition using time delay neural network acoustic modeling with i-vector adaptation. Int. J. Speech Technol. 25(1), 67\u201378 (2022)","journal-title":"Int. J. Speech Technol."},{"key":"212_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12152-3","author":"G Thimmaraja Yadava","year":"2022","unstructured":"Thimmaraja Yadava, G., Nagaraja, B.G., Jayanna, H.S.: A spatial procedure to spectral subtraction for speech enhancement. Multimed. Tools Appl. (2022). https:\/\/doi.org\/10.1007\/s11042-022-12152-3","journal-title":"Multimed. Tools Appl."},{"issue":"3","key":"212_CR32","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1109\/LSP.2014.2302080","volume":"21","author":"F Triefenbach","year":"2014","unstructured":"Triefenbach, F., Demuynck, K., Martens, J.P.: Large vocabulary continuous speech recognition with reservoir-based acoustic models. IEEE Signal Process. Lett. 21(3), 311\u2013315 (2014)","journal-title":"IEEE Signal Process. Lett."},{"issue":"9","key":"212_CR33","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1109\/LSP.2017.2724561","volume":"24","author":"S Ganapathy","year":"2017","unstructured":"Ganapathy, S.: Multivariate autoregressive spectrogram modeling for noisy speech recognition. IEEE Signal Process. Lett. 24(9), 1373\u20131377 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"212_CR34","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1981","volume":"10","author":"Y G\u00f6rmez","year":"2024","unstructured":"G\u00f6rmez, Y.: Customized deep learning based Turkish automatic speech recognition system supported by language model. PeerJ Comput. Sci. 10, e1981 (2024). https:\/\/doi.org\/10.7717\/peerj-cs.1981","journal-title":"PeerJ Comput. Sci."},{"issue":"6","key":"212_CR35","doi-asserted-by":"publisher","first-page":"Article 79, 1\u20131","DOI":"10.1145\/3663568","volume":"23","author":"A Bekarystankyzy","year":"2023","unstructured":"Bekarystankyzy, A., Mamyrbayev, O., Anarbekova, T.: Integrated end-to-end automatic speech recognition for agglutinative languages. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 23(6), Article 79, 1-17 (2023). https:\/\/doi.org\/10.1145\/3663568","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"212_CR36","doi-asserted-by":"publisher","unstructured":"Li, S., Li, J.: Correction while recognition: combining pretrained language model for\u00a0Taiwan-accented speech recognition. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds.) Artificial Neural Networks and Machine Learning\u2014ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14260. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44195-0_32","DOI":"10.1007\/978-3-031-44195-0_32"},{"issue":"3","key":"212_CR37","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1109\/89.232618","volume":"1","author":"Y Zhao","year":"1993","unstructured":"Zhao, Y.: A speaker independent continuous speech recognition system using continuous mixture Gaussian density HMM of phoneme-sized units. IEEE Trans. Speech Audio Process. 1(3), 345\u2013361 (1993)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1","key":"212_CR38","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s00034-019-01189-9","volume":"39","author":"PS Praveen Kumar","year":"2019","unstructured":"Praveen Kumar, P.S., Thimmaraja Yadava, G., Jayanna, H.S.: Continuous Kannada speech recognition system under degraded condition. Circuits Syst. Signal Process. 39(1), 391\u2013419 (2019)","journal-title":"Circuits Syst. Signal Process."}],"container-title":["Iran Journal of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42044-024-00212-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42044-024-00212-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42044-024-00212-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T10:50:21Z","timestamp":1741085421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42044-024-00212-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["212"],"URL":"https:\/\/doi.org\/10.1007\/s42044-024-00212-w","relation":{},"ISSN":["2520-8438","2520-8446"],"issn-type":[{"value":"2520-8438","type":"print"},{"value":"2520-8446","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"23 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}