{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:43:58Z","timestamp":1760255038200,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_8","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:39Z","timestamp":1760253579000},"page":"113-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NAMTalk: From Muscle Vibrations to\u00a0Emotional Speech"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7003-2397","authenticated-orcid":false,"given":"Kunjan","family":"Gajre","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6500-0043","authenticated-orcid":false,"given":"Rajnidhi","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0061-1278","authenticated-orcid":false,"given":"Ravindrakumar M.","family":"Purohit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4068-2005","authenticated-orcid":false,"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational Speech Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964 (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"issue":"4","key":"8_CR2","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.specom.2009.08.002","volume":"52","author":"B Denby","year":"2010","unstructured":"Denby, B., Schultz, T., Honda, K., Hueber, T., Gilbert, J., Brumberg, J.: Silent speech interfaces. Speech Commun. 52(4), 270\u2013287 (2010)","journal-title":"Speech Commun."},{"key":"8_CR3","unstructured":"Goldwater, S., Johnson, M.: Words worth: how robust automatic speech recognition is to speech variations. In: Proceedings of the IEEE Workshop on Spoken Language Technology (SLT), pp.248\u2013253 (2010)"},{"key":"8_CR4","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"8_CR5","unstructured":"Ito, K., Johnson, L.: The LJ Speech dataset (2017). Accessed on 30 July 2025"},{"key":"8_CR6","unstructured":"ITU-T Recommendation P.800: Methods for Subjective Determination of Transmission Quality. Technical report, ITU-T (1996). Accessed 18 Aug 2024"},{"issue":"12","key":"8_CR7","doi-asserted-by":"publisher","first-page":"2375","DOI":"10.1109\/TASLP.2017.2738568","volume":"25","author":"M Janke","year":"2017","unstructured":"Janke, M., Diener, L.: EMG-to-speech: direct generation of speech from facial electromyographic signals. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 25(12), 2375\u20132385 (2017)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"8_CR8","unstructured":"Komatsu, T., Kondo, K., Toda, T., Takeda, K.: Mel-spectral distortion for objective speech quality assessment of noise reduction algorithms. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 521\u2013525. Lujiazui, Shanghai, China (2016)"},{"key":"8_CR9","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis (2020). Accessed 30 July 2025"},{"key":"8_CR10","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 17022\u201317033 (2020)"},{"key":"8_CR11","unstructured":"Koroteev, M.V.: Bert: a review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943 (2021). Accessed 30 July 2025"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Kubichek, R.: Mel-cepstral distance measure for objective speech quality assessment. In: Proceedings of IEEE Pacific Rim Conference on Communications Computers and Signal Processing, vol.\u00a01, pp. 125\u2013128 (1993)","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"8_CR13","unstructured":"Li, Y.A., Han, C., Raghavan, V., Mischler, G., Mesgarani, N.: Styletts 2: towards human-level text-to-speech through style diffusion and adversarial training with large speech language models. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 19594\u201319621 (2023)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Malaviya, H., Shah, J., Patel, M., Munshi, J., Patil, H.A.: MSPEC-NET: multi-domain speech conversion network. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7764\u20137768 (2020)","DOI":"10.1109\/ICASSP40776.2020.9052966"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"McAuliffe, M., Socolof, M., Mihuc, S., Wagner, M., Sonderegger, M.: Montreal forced aligner: trainable text-speech alignment using kaldi. In: Interspeech, vol.\u00a02017, pp. 498\u2013502 (2017)","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"8_CR16","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. arXiv preprint arXiv:2104.09494 (2021). Accessed 30 July 2025","DOI":"10.21437\/Interspeech.2021-299"},{"key":"8_CR17","doi-asserted-by":"publisher","unstructured":"Mu, Z., Yang, X., Zhu, W.: Multi-dimensional and multi-scale modeling for speech separation optimized by discriminative learning. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10094612","DOI":"10.1109\/ICASSP49357.2023.10094612"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Nakajima, Y., Kashioka, H., Shikano, K., Campbell, N.: Non-audible murmur recognition input interface using stethoscopic microphone attached to the skin. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP), vol.\u00a05, pp. V\u2013708 (2003)","DOI":"10.1109\/ICASSP.2003.1200069"},{"issue":"847","key":"8_CR19","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1259\/bjr.71.847.9771379","volume":"71","author":"TW Redpath","year":"1998","unstructured":"Redpath, T.W.: Signal-to-noise ratio in MRI. Br. J. Radiol. 71(847), 704\u2013707 (1998)","journal-title":"Br. J. Radiol."},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Rix, A., Beerends, J., Hollier, M., Hekstra, A.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 749\u2013752 (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Shah, N., Karande, S., Gandhi, V.: Towards improving nam-to-speech synthesis intelligibility using self-supervised speech models. arXiv preprint arXiv:2407.18541 (2024). Accessed 30 July 2025","DOI":"10.21437\/Interspeech.2024-672"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Shah, N., Karande, S., Gandhi, V.: Advancing nam-to-speech conversion with novel methods and the multinam dataset. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10890101"},{"issue":"7","key":"8_CR23","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\u2013frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19(7), 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Toda, T., Nakamura, K., Sekimoto, H., Shikano, K.: Voice conversion for various types of body transmitted speech. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3601\u20133604 (2009)","DOI":"10.1109\/ICASSP.2009.4960405"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Toda, T., Shikano, K.: NAM-to-speech conversion with Gaussian mixture models (2005)","DOI":"10.21437\/Interspeech.2005-611"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Yang, C.Y., Brown, G., Lu, L., Yamagishi, J., King, S.: Noise-robust whispered speech recognition using a non-audible-murmur microphone with vts compensation. In: 8th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 220\u2013223 (2012)","DOI":"10.1109\/ISCSLP.2012.6423522"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:45Z","timestamp":1760253585000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}