{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:15:26Z","timestamp":1783923326339,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234370","type":"print"},{"value":"9789819234387","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3438-7_49","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:44:57Z","timestamp":1783921497000},"page":"578-588","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AdaptiCodec: Pre-quantization Representation Reorganization and Representation-Driven Distortion Allocation for Ultra-Low-Bitrate Neural Speech Coding"],"prefix":"10.1007","author":[{"given":"Shuxian","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"49_CR1","volume-title":"Proceedings of the 135th AES Convention","author":"J-M Valin","year":"2013","unstructured":"Valin, J.-M., Maxwell, G., Terriberry, T.B., Vos, K.: High-quality, low-delay music coding in the opus codec. In: Proceedings of the 135th AES Convention (2013)"},{"key":"49_CR2","first-page":"80","volume-title":"Proceedings TAPR and ARRL 30th Digital Communications Conference","author":"D Rowe","year":"2011","unstructured":"Rowe, D.: Codec 2\u2014open source speech coding at 2400 bits\/s and below. In: Proceedings TAPR and ARRL 30th Digital Communications Conference, pp. 80\u201384 (2011)"},{"key":"49_CR3","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","author":"LM Supplee","year":"1997","unstructured":"Supplee, L.M., Cohn, R.P., Collura, J.S., McCree, A.V.: MELP: the new federal standard at 2400 bps. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2, 1591\u20131594 (1997)"},{"key":"49_CR4","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"A van den Oord","year":"2017","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"49_CR5","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","volume":"30","author":"N Zeghidour","year":"2022","unstructured":"Zeghidour, N., Luebs, A., Omran, A., Skoglund, J., Tagliasacchi, M.: SoundStream: an end-to-end neural audio codec. IEEE Trans. Audio Speech Lang. Process. 30, 495\u2013507 (2022)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"49_CR6","unstructured":"D\u00e9fossez, A., Copet, J., Synnaeve, G., Adi, Y.: High Fidelity Neural Audio Compression. Trans. Mach. Learn. Res. (2023)"},{"key":"49_CR7","unstructured":"Yang, D., Liu, S., Huang, R., Tian, J., Weng, C., Zou, Y.: HiFi-codec: group-residual vector quantization for high fidelity audio codec. arXiv preprint arXiv:2305.02765. (2023)"},{"key":"49_CR8","doi-asserted-by":"crossref","unstructured":"Yu, X., Li, Y., Zhang, P., Lin, L., Cai, T.: MSCACodec: a low-rate neural speech codec with multi-scale residual channel attention. In: Trends in Artificial Intelligence (PRICAI 2024), pp. 346\u2013358 (2025)","DOI":"10.1007\/978-981-96-0125-7_29"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Tu, W., Xiao, L., Xu, X.: SuperCodec: a neural speech codec with selective back-projection network. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 566\u2013570 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447744"},{"key":"49_CR10","first-page":"5206","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","author":"V Panayotov","year":"2015","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: LibriSpeech: an ASR corpus based on public domain audio books. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 5206\u20135210 (2015)"},{"key":"49_CR11","volume-title":"The LJ Speech Dataset","author":"K Ito","year":"2017","unstructured":"Ito, K., Johnson, L.: The LJ Speech Dataset. (2017)"},{"key":"49_CR12","unstructured":"Wang, D., Zhang, X., Zhang, Z.: THCHS-30: a free Chinese speech corpus (2015)"},{"key":"49_CR13","first-page":"862","volume-title":"Recommendation ITU-T P","author":"ITU-T","year":"2001","unstructured":"ITU-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. In: Recommendation ITU-T P.862 (2001)"},{"issue":"7","key":"49_CR14","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., Jensen, J.: An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19(7), 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"49_CR15","first-page":"853","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","author":"A Erell","year":"1990","unstructured":"Erell, A., Weintraub, M.: Estimation using log-spectral-distance criterion for noise-robust speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 853\u2013856 (1990)"},{"key":"49_CR16","volume-title":"Recommendation ITU-R BS.1534-3","author":"ITU-R","year":"2015","unstructured":"ITU-R: Method for the subjective assessment of intermediate quality level of audio systems. In: Recommendation ITU-R BS.1534-3 (2015)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3438-7_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:45:00Z","timestamp":1783921500000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3438-7_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234370","9789819234387"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3438-7_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}