{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:41:01Z","timestamp":1792514461342,"version":"4.5.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819601240","type":"print"},{"value":"9789819601257","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0125-7_29","type":"book-chapter","created":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T03:06:56Z","timestamp":1731812816000},"page":"346-358","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MSCACodec: A Low-Rate Neural Speech Codec With Multi-scale Residual Channel Attention"],"prefix":"10.1007","author":[{"given":"Xingye","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingxia","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"29_CR1","unstructured":"Van Den Oord, A., Dieleman, S., Zen, H., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"29_CR2","unstructured":"Rowe, D.: Codec 2-open source speech coding at 2400 bits\/s and below. In: TAPR and ARRL 30th Digital Communications Conference, pp. 80\u201384 (2011)"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Kleijn, W.B., Lim, F.S.C., Luebs, A., et al.: WaveNet based low-rate speech coding. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 676\u2013680. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Kleijn, W.B., Storus, A., Chinen, M., et al.: Generative speech coding with predictive variance regularization. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6478\u20136482. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Xiao, L., Tu, W., et al.: CQNV: a combination of coarsely quantized bitstream and neural vocoder for low-rate speech coding. arXiv preprint arXiv:2307.13295 (2023)","DOI":"10.21437\/Interspeech.2023-1562"},{"key":"29_CR6","first-page":"17022","volume":"33","author":"J Kong","year":"2020","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. Adv. Neural. Inf. Process. Syst. 33, 17022\u201317033 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR7","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"G\u00e2rbacea, C., van den Oord, A., Li, Y., et al.: Low bit-rate speech coding with VQ-VAE and a WaveNet decoder. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 735\u2013739. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","volume":"30","author":"N Zeghidour","year":"2021","unstructured":"Zeghidour, N., Luebs, A., Omran, A., et al.: SoundStream: an end-to-end neural audio codec. IEEE\/ACM Trans. Audio, Speech Lang. Process. 30, 495\u2013507 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process."},{"key":"29_CR10","unstructured":"D\u00e9fossez, A., Copet, J., Synnaeve, G., et al.: High fidelity neural audio compression. arXiv preprint arXiv:2210.13438 (2022)"},{"key":"29_CR11","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Jenrungrot, T., Chinen, M., Kleijn, W.B., et al.: LMCodec: a low bitrate speech codec with causal transformer models. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Borsos, Z., Marinier, R., Vincent, D., et al.: AudioLM: a language modeling approach to audio generation. Speech, Lang. Process. IEEE\/ACM Trans. Audio (2023)","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"29_CR14","unstructured":"Yang, D., Liu, S., Huang, R., et al.: HiFi-Codec: group-residual vector quantization for high fidelity audio codec. arXiv preprint arXiv:2305.02765 (2023)"},{"key":"29_CR15","unstructured":"Ji, S., Fang, M., Jiang, Z., et al.: Language-Codec: reducing the gaps between discrete codec representation and speech language models. arXiv preprint arXiv:2402.12208 (2024)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Xu, L., Jiang, J., Zhang, D., et al.: An intra-BRNN and GB-RVQ based end-to-end neural audio codec. arXiv preprint arXiv:2402.01271 (2024)","DOI":"10.21437\/Interspeech.2023-537"},{"key":"29_CR17","unstructured":"Li, K., Yang, R., Hu, X.: An efficient encoder-decoder architecture with top-down attention for speech separation. arXiv preprint arXiv:2209.15200 (2022)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, Z., Tuo, D., et al.: FullSubNet+: channel attention FullSubNet with complex spectrograms for speech enhancement. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7857\u20137861. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747888"},{"key":"29_CR19","doi-asserted-by":"publisher","unstructured":"Li, J., Fang, F., Mei, K., Zhang, G.: Multi-scale residual network for image super-resolution. Comput. Vis. ECCV. Lect. Notes Comput. Sci. 2018, 527\u2013542 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-332","DOI":"10.1007\/978-3-030-01237-332"},{"key":"29_CR20","doi-asserted-by":"publisher","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional feature fusion. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA (2021). https:\/\/doi.org\/10.1109\/wacv48630.2021.00360","DOI":"10.1109\/wacv48630.2021.00360"},{"key":"29_CR21","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv: Learning (2018)"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Luo, Y., Mesgarani, N.: TasNet: time-domain audio separation network for real-time, single-channel speech separation. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 696\u2013700. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., et al.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"29_CR24","unstructured":"Ito, K., Johnson, L.: The LJ speech dataset (2017). https:\/\/keithito.com\/LJ-Speech-Dataset\/"},{"key":"29_CR25","unstructured":"Wang, D., Zhang, X.: THCHS-30: a free Chinese speech corpus. arXiv preprint arXiv:1512.01882 (2015)"},{"key":"29_CR26","unstructured":"MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability 1(14), 281\u2013297 (1967)"},{"key":"29_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"29_CR28","unstructured":"Recommendation I T U T. Perceptual evaluation of speech quality (PESQ): an objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs. Rec. ITU-T P. 862 (2001)"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., et al.: A short-time objective intelligibility measure for time-frequency weighted noisy speech. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4214\u20134217. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Erell, A., Weintraub, M.: Estimation using log-spectral-distance criterion for noise-robust speech recognition. In: International Conference on Acoustics, Speech, and Signal Processing, pp. 853\u2013856. IEEE (1990)","DOI":"10.1109\/ICASSP.1990.115972"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Chinen, M., Lim, F.S.C., Skoglund, J., et al.: ViSQOL v3: an open source production ready objective speech and audio metric. In: 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"29_CR32","unstructured":"Valin, J.M., Vos, K., Terriberry, T.: Definition of the opus audio codec (2012)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0125-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T04:31:08Z","timestamp":1731817868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0125-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601240","9789819601257"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0125-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}