{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:02:13Z","timestamp":1773259333142,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T00:00:00Z","timestamp":1681084800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T00:00:00Z","timestamp":1681084800000},"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":["SIViP"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11760-023-02559-2","type":"journal-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T09:02:52Z","timestamp":1681117372000},"page":"3377-3385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Non-intrusive speech quality assessment with attention-based ResNet-BiLSTM"],"prefix":"10.1007","volume":"17","author":[{"given":"Kailai","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diqun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JinXing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengbin","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,10]]},"reference":[{"issue":"6","key":"2559_CR1","doi-asserted-by":"publisher","first-page":"1935","DOI":"10.1109\/TASL.2006.883253","volume":"14","author":"TH Falk","year":"2006","unstructured":"Falk, T.H., Chan, W.-Y.: Single-ended speech quality measurement using machine learning methods. IEEE Trans. Audio Speech Lang. Process. 14(6), 1935\u20131947 (2006). https:\/\/doi.org\/10.1109\/TASL.2006.883253","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2559_CR2","unstructured":"Union, I.T.: Single-ended method for objective speech quality assessment in narrowband telephony applications. ITU-T Recommendation P. 563 (2004)"},{"key":"2559_CR3","doi-asserted-by":"crossref","unstructured":"Wong, J.W.: Signal-to-noise ratio (SNR). Encycl. Neurosci. 3690\u20133690 (2009)","DOI":"10.1007\/978-3-540-29678-2_5394"},{"key":"2559_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-0613-6_17408","volume-title":"Signal-to-Distortion Ratio","author":"MH Weik","year":"2000","unstructured":"Weik, M.H.: Signal-to-Distortion Ratio. Springer, New York (2000)"},{"key":"2559_CR5","unstructured":"Rao, V., Rao, P., Tun, G.N.: Signal to interference ratio (SIR)-10 dB (2012)"},{"key":"2559_CR6","unstructured":"Cernak, M., Rusko, M.: An evaluation of synthetic speech using the PESQ measure. In: Proceedings of Forum Acusticum, pp. 2725\u20132728 (2005)"},{"key":"2559_CR7","unstructured":"Huang, D.-Y.: Prediction of perceived sound quality of synthetic speech. Asia-Pacific Signal and Information Processing Association (APSIPA) (2011)"},{"key":"2559_CR8","unstructured":"Remes, U., Karhila, R., Kurimo, M.: Objective evaluation measures for speaker-adaptive HMM-TTS systems. In: Eighth ISCA Workshop on Speech Synthesis (SSW) (2013)"},{"key":"2559_CR9","doi-asserted-by":"crossref","unstructured":"Yoshimura, T., Henter, G.E., Watts, O., Wester, M., Yamagishi, J., Tokuda, K.: A hierarchical predictor of synthetic speech naturalness using neural networks. In: INTERSPEECH, pp. 342\u2013346 (2016)","DOI":"10.21437\/Interspeech.2016-847"},{"key":"2559_CR10","unstructured":"Patton, B., Agiomyrgiannakis, Y., Terry, M., Wilson, K., Saurous, R.A., Sculley, D.: AutoMOS: learning a non-intrusive assessor of naturalness-of-speech. arXiv preprint arXiv:1611.09207 (2016)"},{"key":"2559_CR11","doi-asserted-by":"crossref","unstructured":"Avila, A.R., Gamper, H., Reddy, C., Cutler, R., Tashev, I., Gehrke, J.: Non-intrusive speech quality assessment using neural networks. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 631\u2013635 (2019). IEEE","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"2559_CR12","doi-asserted-by":"crossref","unstructured":"Fu, S.-W., Tsao, Y., Hwang, H.-T., Wang, H.-M.: Quality-Net: an end-to-end non-intrusive speech quality assessment model based on BLSTM. arXiv preprint arXiv:1808.05344 (2018)","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"2559_CR13","doi-asserted-by":"crossref","unstructured":"Lo, C.-C., Fu, S.-W., Huang, W.-C., Wang, X., Yamagishi, J., Tsao, Y., Wang, H.-M.: MOSNet: deep learning based objective assessment for voice conversion. arXiv preprint arXiv:1904.08352 (2019)","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"2559_CR14","doi-asserted-by":"crossref","unstructured":"Tseng, W.-C., Huang, C.-Y., Kao, W.-T., Lin, Y.Y., Lee, H.-Y.: Utilizing self-supervised representations for MOS prediction. In: INTERSPEECH, pp. 2781\u20132785 (2021)","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"2559_CR15","doi-asserted-by":"publisher","unstructured":"Leng, Y., Tan, X., Zhao, S., Soong, F., Li, X.-Y., Qin, T.: MBNet: MOS prediction for synthesized speech with mean-bias network. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 391\u2013395 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413877","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"2559_CR16","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2559_CR17","doi-asserted-by":"crossref","unstructured":"Mittag, G., Cutler, R., Hosseinkashi, Y., Revow, M., Srinivasan, S., Chande, N., Aichner, R.: DNN no-reference PSTN speech quality rrediction. In: INTERSPEECH (2020)","DOI":"10.21437\/Interspeech.2020-2760"},{"key":"2559_CR18","doi-asserted-by":"crossref","unstructured":"McFee, B., Raffel, C., Liang, D., Ellis, D.P., McVicar, M., Battenberg, E., Nieto, O.: Librosa: audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference (SciPy2015), vol. 8, pp. 18\u201325. Citeseer (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"2559_CR19","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning (ICML) (2010)"},{"key":"2559_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), pp. 448\u2013456 (2015)"},{"key":"2559_CR21","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/TASLP.2020.3036237","volume":"29","author":"M Yousefi","year":"2021","unstructured":"Yousefi, M., Hansen, J.H.L.: Block-based high performance CNN architectures for frame-level overlapping speech detection. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 28\u201340 (2021). https:\/\/doi.org\/10.1109\/TASLP.2020.3036237","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2559_CR22","doi-asserted-by":"publisher","unstructured":"Chun, C., Jeon, K.M., Leem, C., Lee, B., Choi, W.: Comparison of CNN-based speech dereverberation using neural vocoder. In: International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 251\u2013254 (2021). https:\/\/doi.org\/10.1109\/ICAIIC51459.2021.9415259","DOI":"10.1109\/ICAIIC51459.2021.9415259"},{"key":"2559_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2559_CR24","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Schl\u00fcter, R., Ney, H.: LSTM neural networks for language modeling. In: INTERSPEECH (2012)","DOI":"10.21437\/Interspeech.2012-65"},{"key":"2559_CR25","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Vyas, P., Dong, X., Williamson, D.S.: An end-to-end non-intrusive model for subjective and objective real-world speech assessment using a multi-task framework. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 316\u2013320 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414182","DOI":"10.1109\/ICASSP39728.2021.9414182"},{"key":"2559_CR26","doi-asserted-by":"publisher","unstructured":"Miao, H., Cheng, G., Gao, C., Zhang, P., Yan, Y.: Transformer-based online CTC\/attention end-to-end speech recognition architecture. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6084\u20136088 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053165","DOI":"10.1109\/ICASSP40776.2020.9053165"},{"key":"2559_CR27","doi-asserted-by":"publisher","unstructured":"Yang, C.-H., Qi, J., Chen, P.-Y., Ma, X., Lee, C.-H.: Characterizing speech adversarial examples using self-attention U-Net enhancement. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3107\u20133111 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053288","DOI":"10.1109\/ICASSP40776.2020.9053288"},{"key":"2559_CR28","doi-asserted-by":"crossref","unstructured":"Yi, G., Xiao, W., Xiao, Y., Naderi, B., M\u00f6ller, S., Wardah, W., Mittag, G., Culter, R., Zhang, Z., Williamson, D.S., Chen, F., Yang, F., Shang, S.: Conferencing Speech 2022 challenge: non-intrusive objective speech quality assessment (NISQA) challenge for online conferencing applications. In: INTERSPEECH (2022)","DOI":"10.21437\/Interspeech.2022-10597"},{"key":"2559_CR29","doi-asserted-by":"crossref","unstructured":"Mittag, G., Naderi, B., Chehadi, A., M\u00f6ller, S.: NISQA: a deep CNN-self-attention model for multidimensional speech quality prediction with crowdsourced datasets. In: INTERSPEECH, pp. 2127\u20132131 (2021)","DOI":"10.21437\/Interspeech.2021-299"},{"key":"2559_CR30","doi-asserted-by":"crossref","unstructured":"Dong, X., Williamson, D.S.: A pyramid recurrent network for predicting crowdsourced speech-quality ratings of real-world signals, pp. 4631\u20134635 (2020)","DOI":"10.21437\/Interspeech.2020-2809"},{"issue":"1","key":"2559_CR31","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"2559_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"2559_CR33","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265\u2013283 (2016)"},{"key":"2559_CR34","doi-asserted-by":"crossref","unstructured":"Malfait, L., Berger, J., Kastner, M.: P. 563\u2014the ITU-T standard for single-ended speech quality assessment. IEEE Trans. Audio Speech Lang. Process. 14(6), 1924\u20131934 (2006)","DOI":"10.1109\/TASL.2006.883177"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02559-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-023-02559-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-023-02559-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T11:45:14Z","timestamp":1744199114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-023-02559-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,10]]},"references-count":34,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["2559"],"URL":"https:\/\/doi.org\/10.1007\/s11760-023-02559-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2170880\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,10]]},"assertion":[{"value":"16 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2023","order":4,"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"}},{"value":"This declaration is not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}