{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:02:15Z","timestamp":1789981335815,"version":"4.0.1"},"reference-count":38,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T00:00:00Z","timestamp":1789862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>In recent years, the application of multi-scale residuals and attention mechanisms in automatic speech recognition has made some progress. However, existing speech recognition systems still have critical limitations. Many existing systems fail to adequately capture multi-scale speech features, struggling with representation gaps and often relying on inefficient serial attention mechanisms. Additionally, lightweight models, while efficient, often isolate information within grouped architectures, limiting the global feature interaction necessary for speech recognition. To address these persistent challenges, we introduce MSRDA-GSCA, an architecture that synergistically integrates a Multi-Scale Residual Deep Convolutional Attention (MSRDA) network with a Group Shuffled Co-Attention (GSCA) mechanism. MSRDA uses parallel convolutions with varied kernels and dilations, plus adaptive residual connections, to capture diverse temporal dependencies and align heterogeneous features. Its dual-path attention recalibrates channel and spatial information with element-wise max fusion. GSCA employs sequential position-wise channel and spatial attention with intermediate channel shuffling, enabling cross-group interaction and enhancing global feature synergy. Experiments on THCHS-30 and ST-CMDS datasets show that the proposed model outperforms existing methods in Character Error Rate (CER) and Word Error Rate (WER). Ablation studies confirm the complementarity of MSRDA and GSCA. With only 4.65 M parameters, MSRDA-GSCA achieves high recognition accuracy while maintaining low computational complexity for efficient deployment.<\/jats:p>","DOI":"10.3390\/e28091037","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:03:47Z","timestamp":1789977827000},"page":"1037","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Scale Residual Attention Network for Chinese Speech Recognition Through Collaborative Design"],"prefix":"10.3390","volume":"28","author":[{"given":"Yuying","family":"Li","sequence":"first","affiliation":[{"name":"Department of Information Engineering, Beijing University of Chemical Technology, No.15 North Third Ring East Road, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjie","family":"Wan","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Beijing University of Chemical Technology, No.15 North Third Ring East Road, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6705-2972","authenticated-orcid":false,"given":"Akash","family":"Sutradhar","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Beijing University of Chemical Technology, No.15 North Third Ring East Road, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianing","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Beijing University of Chemical Technology, No.15 North Third Ring East Road, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Yang, H., Shangguan, Y., Wang, D., Li, M., Chuang, P., Zhang, X., Venkatesh, G., Kalinli, O., and Chandra, V. (2022). Omni-Sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR Via Supernet. ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP43922.2022.9746469"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Maruf, M.R., Faruque, M.O., Mahmood, S., Nelima, N.N., Muhtasim, M.G., and Pervez, M.J.A. (2020). Effects of Noise on RASTA-PLP and MFCC based Bangla ASR Using CNN. 2020 IEEE Region 10 Symposium (TENSYMP), IEEE.","DOI":"10.1109\/TENSYMP50017.2020.9231034"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Thomas, S., Kingsbury, B., Saon, G., and Kuo, H.-K.J. (2022). Integrating Text Inputs for Training and Adapting RNN Transducer ASR Models. ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP43922.2022.9747862"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., and Schmidhuber, J. (2006). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. Proceedings of the 23rd International Conference on Machine Learning, Association for Computing Machinery.","DOI":"10.1145\/1143844.1143891"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Deng, K., and Woodland, P.C. (2024). FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training. ICASSP 2024\u20142024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP48485.2024.10447838"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., and Vinyals, O. (2016). Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"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. Interspeech 2020, ISCA.","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref_8","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., and Auli, M. (2020). Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. Advances in Neural Information Processing Systems, Curran Associates, Inc.. Available online: https:\/\/papers.nips.cc\/paper\/2020\/hash\/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Babu, A., Wang, C., Tjandra, A., Lakhotia, K., Xu, Q., Goyal, N., Singh, K., von Platen, P., Saraf, Y., and Pino, J. (2022). XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale. Interspeech 2022, ISCA.","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Han, K.J., Prieto, R., and Ma, T. (2019). State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention with Dilated 1D Convolutions. 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), IEEE.","DOI":"10.1109\/ASRU46091.2019.9003730"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kriman, S., Beliaev, S., Ginsburg, B., Huang, J., Kuchaiev, O., Lavrukhin, V., Leary, R., Li, J., and Zhang, Y. (2020). Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions. ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, S., Lu, X., Sken, P., Takashima, R., Kawahara, T., and Kawai, H. (2017). Incremental training and constructing the very deep convolutional residual network acoustic models. 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), IEEE.","DOI":"10.1109\/ASRU.2017.8268939"},{"key":"ref_14","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"Volume 1","author":"Chorowski","year":"2015","journal-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1080\/03772063.2025.2462789","article-title":"MF-MSCNN: Multi-Feature based Multi-Scale Convolutional Neural Network for Image Dehazing via Input Transformation","volume":"71","author":"Kumar","year":"2025","journal-title":"IETE J. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","article-title":"Convolutional Neural Networks for Speech Recognition","volume":"22","author":"Mohamed","year":"2014","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_17","unstructured":"Chen, C.-F., Fan, Q., Mallinar, N., Sercu, T., and Feris, R. (May, January 30). Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada. Available online: https:\/\/openreview.net\/forum?id=HJMHpjC9Ym."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rownicka, J., Bell, P., and Renals, S. (2020). Multi-Scale Octave Convolutions for Robust Speech Recognition. ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP40776.2020.9053703"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s13636-024-00341-x","article-title":"Supervised Attention Multi-Scale Temporal Convolutional Network for monaural speech enhancement","volume":"2024","author":"Zhang","year":"2024","journal-title":"J. Audio Speech Music Process."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Vydana, H.K., and Vuppala, A.K. (September, January 28). Residual neural networks for speech recognition. Proceedings of the 2017 25th European Signal Processing Conference (EUSIPCO), Kos, Greece.","DOI":"10.23919\/EUSIPCO.2017.8081266"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bozheniuk, V., Zeyer, A., Schluter, R., and Ney, H. (2020). A Comprehensive Study of Residual CNNS for Acoustic Modeling in ASR. ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP40776.2020.9052931"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., and He, K. (2017). Aggregated Residual Transformations for Deep Neural Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e70020","DOI":"10.1049\/ell2.70020","article-title":"End-to-end speech-denoising deep neural network based on residual-attention gated linear units","volume":"60","author":"Kim","year":"2024","journal-title":"Electron. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, M., Do, C.-T., and Doddipatla, R. (2023). Cumulative Attention Based Streaming Transformer ASR with Internal Language Model Joint Training and Rescoring. ICASSP 2023\u20142023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP49357.2023.10094800"},{"key":"ref_26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is All you Need. Advances in Neural Information Processing Systems, Curran Associates, Inc.. Available online: https:\/\/papers.nips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101598","DOI":"10.1016\/j.csl.2023.101598","article-title":"A novel channel estimate for noise robust speech recognition","volume":"86","author":"Vanderreydt","year":"2024","journal-title":"Comput. Speech Lang."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.neuroimage.2008.06.046","article-title":"Look who\u2019s talking: The deployment of visuo-spatial attention during multisensory speech processing under noisy environmental conditions","volume":"43","author":"Senkowski","year":"2008","journal-title":"NeuroImage"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ho, M.T., Lee, J., Lee, B.-K., Yi, D.H., and Kang, H.-G. (2020). A Cross-Channel Attention-Based Wave-U-Net for Multi-Channel Speech Enhancement. Interspeech 2020, ISCA.","DOI":"10.21437\/Interspeech.2020-2548"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1564","DOI":"10.1109\/TCDS.2021.3123979","article-title":"Convolutional-Recurrent Neural Networks with Multiple Attention Mechanisms for Speech Emotion Recognition","volume":"14","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref_31","unstructured":"Shuai, G., Zou, T., Huang, Y., and Zhang, X. (2024, September 25). nl8590687\/ASRT_SpeechRecognition: ASRT v1.3.0 Released. (20 May 2022). Zenodo. Available online: https:\/\/zenodo.org\/records\/6566359."},{"key":"ref_32","unstructured":"Wang, D., and Zhang, X. (2015). THCHS-30: A Free Chinese Speech Corpus. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Guo, L., Deng, Y., Tang, L., Fan, R., Yan, B., and Xiao, Z. (2023, January 6\u20138). A Chinese Speech Recognition System Based on Binary Neural Network and Pre-processing. Proceedings of the 2023 6th World Conference on Computing and Communication Technologies (WCCCT), Virtual.","DOI":"10.1109\/WCCCT56755.2023.10052123"},{"key":"ref_34","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., and Chen, G. Deep speech 2: End-to-end speech recognition in English and mandarin. Proceedings of the 33rd International Conference on International Conference on Machine Learning, JMLR.org."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"105659","DOI":"10.1016\/j.dsp.2025.105659","article-title":"Chinese speech recognition based on improved end-to-end transformer learning model","volume":"168","author":"Wang","year":"2026","journal-title":"Digit. Signal Process."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, S., Lei, M., Yan, Z., and Dai, L. (2018). Deep-FSMN for Large Vocabulary Continuous Speech Recognition. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"ref_37","first-page":"699","article-title":"TCN-Transformer-CTC for end-to-end speech recognition","volume":"39","author":"Xie","year":"2022","journal-title":"Comput. Appl. Res."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zhang, Y., and Xu, M. (2020, January 6\u20138). A Novel Speech Recognition Model with Bayesian Optimization. Proceedings of the 2020 Chinese Automation Congress (CAC), Shanghai, China.","DOI":"10.1109\/CAC51589.2020.9327073"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/9\/1037\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:06:17Z","timestamp":1789977977000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/9\/1037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,20]]},"references-count":38,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["e28091037"],"URL":"https:\/\/doi.org\/10.3390\/e28091037","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,20]]}}}