{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:28:39Z","timestamp":1777631319214,"version":"3.51.4"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032243492","type":"print"},{"value":"9783032243508","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-24350-8_23","type":"book-chapter","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:25:30Z","timestamp":1777433130000},"page":"347-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classifying Audio Timbre Without Audio Using Text-Only Training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0183-6482","authenticated-orcid":false,"given":"Peter","family":"McCabe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1033-5931","authenticated-orcid":false,"given":"Patrick J.","family":"Donnelly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"23_CR1","unstructured":"Al-Jaff, M.: Messing with the Gap: On the Modality Gap Phenomenon in Multimodal Contrastive Representation Learning. Ph.D. thesis, Uppsala University (2023)"},{"key":"23_CR2","unstructured":"Aucouturier, J., Pachet, F.: Improving timbre similarity: how high\u2019s the sky? J. Negat. Res. Speech Audio Sci. (JNRSAS) (2004)"},{"key":"23_CR3","doi-asserted-by":"publisher","unstructured":"Bogdanov, D., Minz, W., Tovstogan, P., Porter, A.: Mtg-jamendo dataset (2019). https:\/\/doi.org\/10.5281\/ZENODO.3826813","DOI":"10.5281\/ZENODO.3826813"},{"issue":"2","key":"23_CR4","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1504\/JDR.2017.086749","volume":"15","author":"M Carron","year":"2017","unstructured":"Carron, M., Rotureau, T., Dubois, F., Misdariis, N., Susini, P.: Speaking about sounds: a tool for communication on sound features. J. Des. Res. 15(2), 85 (2017). https:\/\/doi.org\/10.1504\/JDR.2017.086749","journal-title":"J. Des. Res."},{"key":"23_CR5","doi-asserted-by":"publisher","unstructured":"Chen, H., He, L., Liu, Y., Yang, L.: Visual neural decoding via improved visual-EEG semantic consistency (2024). https:\/\/doi.org\/10.48550\/arXiv.2408.06788. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2408.06788"},{"key":"23_CR6","doi-asserted-by":"publisher","unstructured":"Chu, A., O\u2019Reilly, P., Barnett, J., Pardo, B.: Text2FX: harnessing clap embeddings for text-guided audio effects. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2025). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10890334, iSSN: 2379-190X","DOI":"10.1109\/ICASSP49660.2025.10890334"},{"key":"23_CR7","doi-asserted-by":"publisher","unstructured":"Czedik-Eysenberg, I., Reuter, C.: Evaluating timbre-related audio descriptors across different libraries and multimodal embeddings. In: Proceedings of DAS|DAGA 2025 (2025). https:\/\/doi.org\/10.71568\/dasdaga2025.657","DOI":"10.71568\/dasdaga2025.657"},{"key":"23_CR8","doi-asserted-by":"publisher","unstructured":"Deshmukh, S., Elizalde, B., Emmanouilidou, D., Raj, B., Singh, R., Wang, H.: Training audio captioning models without audio. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea, pp. 371\u2013375. IEEE (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448115","DOI":"10.1109\/ICASSP48485.2024.10448115"},{"key":"23_CR9","unstructured":"Doh, S., Choi, K., Lee, J., Nam, J.: LP-MusicCaps: LLM-based pseudo music captioning. In: Proceedings of the 24th International Society for Music Information Retrieval Conference, pp. 409\u2013416 (2023)"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Dong, H.W., et al.: CLIPSonic: text-to-audio synthesis with unlabeled videos and pretrained language-vision models. In: 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, pp.\u00a01\u20135. IEEE (2023). https:\/\/doi.org\/10.1109\/WASPAA58266.2023.10248160","DOI":"10.1109\/WASPAA58266.2023.10248160"},{"key":"23_CR11","doi-asserted-by":"publisher","unstructured":"D\u2019Orazio, A., Briglia, M.R., Crisostomi, D., Loi, D., Rodol\u00e0, E., Masi, I.: Implicit inversion turns CLIP into a decoder (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.23161. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2505.23161"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"Drossos, K., Lipping, S., Virtanen, T.: Clotho: an audio captioning dataset. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 736\u2013740. IEEE (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9052990","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Elizalde, B., Deshmukh, S., Ismail, M.A., Wang, H.: CLAP learning audio concepts from natural language supervision. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095889, ISSN: 2379-190X","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"23_CR14","doi-asserted-by":"publisher","unstructured":"Elizalde, B., Deshmukh, S., Wang, H.: Natural language supervision for general-purpose audio representations. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea, pp. 336\u2013340. IEEE (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448504","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"issue":"1","key":"23_CR15","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/1687-4722-2011-11","volume":"2011","author":"R Ferrer","year":"2011","unstructured":"Ferrer, R., Eerola, T.: Semantic structures of timbre emerging from social and acoustic descriptions of music. EURASIP J. Audio Speech Music Process. 2011(1), 11 (2011). https:\/\/doi.org\/10.1186\/1687-4722-2011-11","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"Grattafiori, A., et al.: The Llama 3 herd of models (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.21783. Accessed 25 Oct 2025","DOI":"10.48550\/arXiv.2407.21783"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Gu, S., Clark, C., Kembhavi, A.: I can\u2019t believe there\u2019s no images!: learning visual tasks using only language supervision. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2672\u20132683 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00252, ISSN: 2380-7504","DOI":"10.1109\/ICCV51070.2023.00252"},{"key":"23_CR18","doi-asserted-by":"publisher","unstructured":"Guinot, J., Riou, A., Quinton, E., Fazekas, G.: SLAP: Siamese language-audio pretraining without negative samples for music understanding (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.17815, ISMIR 2025, Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2506.17815"},{"issue":"1","key":"23_CR19","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1076\/jnmr.32.1.3.16798","volume":"32","author":"P Herrera-Boyer","year":"2003","unstructured":"Herrera-Boyer, P., Peeters, G., Dubnov, S.: Automatic classification of musical instrument sounds. J. New Music Res. 32(1), 3\u201321 (2003). https:\/\/doi.org\/10.1076\/jnmr.32.1.3.16798","journal-title":"J. New Music Res."},{"key":"23_CR20","doi-asserted-by":"publisher","unstructured":"Hu, R., et al.: Vela: scalable embeddings with voice large language models for multimodal retrieval. In: Interspeech 2025, pp. 2640\u20132644. ISCA (2025). https:\/\/doi.org\/10.21437\/Interspeech.2025-159","DOI":"10.21437\/Interspeech.2025-159"},{"key":"23_CR21","doi-asserted-by":"publisher","unstructured":"Jang, Y.K., Lim, S.N.: Towards cross-modal backward-compatible representation learning for vision-language models (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.14715. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2405.14715"},{"key":"23_CR22","doi-asserted-by":"publisher","unstructured":"Jiang, W., Liu, J., Li, Z., Zhu, J., Zhang, X., Wang, S.: Analysis and modeling of timbre perception features of Chinese musical instruments. In: 2019 IEEE\/ACIS 18th International Conference on Computer and Information Science (ICIS), Beijing, China, pp. 191\u2013195. IEEE (2019). https:\/\/doi.org\/10.1109\/ICIS46139.2019.8940168","DOI":"10.1109\/ICIS46139.2019.8940168"},{"key":"23_CR23","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1109\/TASLP.2020.2993893","volume":"28","author":"KL Kim","year":"2020","unstructured":"Kim, K.L., Lee, J., Kum, S., Park, C.L., Nam, J.: Semantic tagging of singing voices in popular music recordings. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 1656\u20131668 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.2993893","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"23_CR24","doi-asserted-by":"publisher","unstructured":"Kong, Z., et al.: Improving text-to-audio models with synthetic captions (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.15487. Accessed 29 Oct 2024","DOI":"10.48550\/arXiv.2406.15487"},{"key":"23_CR25","unstructured":"Kouzelis, T., Katsouros, V.: Weakly-supervised automated audio captioning via text only training. In: Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023), Tampere, Finland, pp. 81\u201385 (2023)"},{"key":"23_CR26","unstructured":"Lavengood, M.: A New Approach to the Analysis of Timbre. Ph.D. thesis, CUNY Academic Works (2017)"},{"key":"23_CR27","doi-asserted-by":"publisher","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (2022). https:\/\/doi.org\/10.48550\/arXiv.2201.12086. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2201.12086"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Liang, W., Zhang, Y., Kwon, Y., Yeung, S., Zou, J.: Mind the gap: understanding the modality gap in multi-modal contrastive representation learning. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. NIPS \u201922, Red Hook, NY, USA, pp. 17612\u201317625. Curran Associates Inc. (2022)","DOI":"10.52202\/068431-1280"},{"key":"23_CR29","unstructured":"Limberg, C., Schulz, F., Zhang, Z., Weinzierl, S.: Pitch-conditioned instrument sound synthesis from an interactive timbre latent space. In: Gabrielli, L., Cecchi, S. (eds.) Proceedings of the 28-th International Conference on Digital Audio Effects (DAFx25), Italy, pp. 433\u2013440. Ancona (2025)"},{"key":"23_CR30","doi-asserted-by":"publisher","unstructured":"Liu, Z., Liu, J., Ma, F.: Improving cross-modal alignment with synthetic pairs for text-only image captioning. In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u201924\/IAAI\u201924\/EAAI\u201924, vol.\u00a038, pp. 3864\u20133872. AAAI Press (2024). https:\/\/doi.org\/10.1609\/aaai.v38i4.28178","DOI":"10.1609\/aaai.v38i4.28178"},{"key":"23_CR31","doi-asserted-by":"publisher","unstructured":"Ma, H., et al.: Language-queried target sound extraction without parallel training data. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, pp.\u00a01\u20135. IEEE (2025). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10887543","DOI":"10.1109\/ICASSP49660.2025.10887543"},{"key":"23_CR32","doi-asserted-by":"publisher","unstructured":"Ma, H., Peng, Z., Li, X., Shao, M., Wu, X., Liu, J.: CLAPSep: leveraging contrastive pre-trained model for multi-modal query-conditioned target sound extraction. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 4945\u20134960 (2024). https:\/\/doi.org\/10.1109\/taslp.2024.3497586, publisher: Institute of Electrical and Electronics Engineers (IEEE)","DOI":"10.1109\/taslp.2024.3497586"},{"key":"23_CR33","doi-asserted-by":"publisher","unstructured":"Mannone, M., Distefano, V., Santini, G.: Classes of colors and timbres: a clustering approach. Electron. J. Appl. Stat. Anal. 15(3), 588\u2013605 (2022). https:\/\/doi.org\/10.1285\/i20705948v15n3p588, number: 3","DOI":"10.1285\/i20705948v15n3p588"},{"issue":"1","key":"23_CR34","doi-asserted-by":"publisher","first-page":"21445","DOI":"10.1038\/s41598-024-72071-1","volume":"14","author":"R Marjieh","year":"2024","unstructured":"Marjieh, R., Sucholutsky, I., Van Rijn, P., Jacoby, N., Griffiths, T.L.: Large language models predict human sensory judgments across six modalities. Sci. Rep. 14(1), 21445 (2024). https:\/\/doi.org\/10.1038\/s41598-024-72071-1","journal-title":"Sci. Rep."},{"key":"23_CR35","doi-asserted-by":"publisher","unstructured":"Mei, X., et al.: WavCaps: a ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 3339\u20133354 (2024). https:\/\/doi.org\/10.1109\/taslp.2024.3419446, publisher: Institute of Electrical and Electronics Engineers (IEEE)","DOI":"10.1109\/taslp.2024.3419446"},{"key":"23_CR36","doi-asserted-by":"publisher","unstructured":"Nukrai, D., Mokady, R., Globerson, A.: Text-only training for image captioning using noise-injected CLIP. In: Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, pp. 4055\u20134063. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.299","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"23_CR37","doi-asserted-by":"publisher","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2019). https:\/\/doi.org\/10.48550\/arXiv.1807.03748. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.1807.03748"},{"issue":"3","key":"23_CR38","doi-asserted-by":"publisher","first-page":"466","DOI":"10.3390\/app9030466","volume":"9","author":"A Pearce","year":"2019","unstructured":"Pearce, A., Brookes, T., Mason, R.: Modelling timbral hardness. Appl. Sci. 9(3), 466 (2019). https:\/\/doi.org\/10.3390\/app9030466","journal-title":"Appl. Sci."},{"key":"23_CR39","doi-asserted-by":"publisher","unstructured":"Pearce, A., Brookes, T., Mason, R.: Timbral Characterisation Tool v0.2 Development Dataset (2019). https:\/\/doi.org\/10.5281\/zenodo.2545496. Accessed 02 Aug 2024","DOI":"10.5281\/zenodo.2545496"},{"key":"23_CR40","unstructured":"Pearce, A., Safavi, S., Tim, B., Mason, Russell\u00a0Wang, W., Plumbley, M.: D5.8: release of timbral characterisation tools for semantically annotating non-musical content (2019). https:\/\/audiocommons.github.io\/materials\/. Accessed 1 Feb 2026"},{"key":"23_CR41","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR42","doi-asserted-by":"publisher","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data (2020). https:\/\/doi.org\/10.48550\/arXiv.2001.07966. Accessed 22 Jul 2024","DOI":"10.48550\/arXiv.2001.07966"},{"key":"23_CR43","doi-asserted-by":"publisher","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020. Accessed 30 Sept 2025","DOI":"10.48550\/arXiv.2103.00020"},{"key":"23_CR44","doi-asserted-by":"publisher","unstructured":"Ramasinghe, S., Shevchenko, V., Avraham, G., Thalaiyasingam, A.: Accept the modality gap: an exploration in the hyperbolic space. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 27253\u201327262. IEEE (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02574","DOI":"10.1109\/CVPR52733.2024.02574"},{"key":"23_CR45","doi-asserted-by":"publisher","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip Latents (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.06125. Accessed 13 Jul 2025","DOI":"10.48550\/arXiv.2204.06125"},{"key":"23_CR46","doi-asserted-by":"publisher","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 3980\u20133990. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"23_CR47","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.796422","volume":"13","author":"L Reymore","year":"2022","unstructured":"Reymore, L., Beauvais-Lacasse, E., Smith, B.K., McAdams, S.: Modeling noise-related timbre semantic categories of orchestral instrument sounds with audio features, pitch register, and instrument family. Front. Psychol. 13, 796422 (2022). https:\/\/doi.org\/10.3389\/fpsyg.2022.796422","journal-title":"Front. Psychol."},{"key":"23_CR48","doi-asserted-by":"publisher","unstructured":"Reymore, L., Huron, D.: Using auditory imagery tasks to map the cognitive linguistic dimensions of musical instrument timbre qualia. Psychomusicology: Music, Mind, and Brain 30(3), 124\u2013144 (2020). https:\/\/doi.org\/10.1037\/pmu0000263, place: US Publisher: Educational Publishing Foundation","DOI":"10.1037\/pmu0000263"},{"key":"23_CR49","doi-asserted-by":"publisher","unstructured":"Reymore, L., Noble, J., Saitis, C., Traube, C., Wallmark, Z.: Timbre semantic associations vary both between and within instrumentsan empirical study incorporating register and pitch height. Music. Percept. 40(3), 253\u2013274 (023). https:\/\/doi.org\/10.1525\/mp.2023.40.3.253, publisher: University of California Press","DOI":"10.1525\/mp.2023.40.3.253"},{"key":"23_CR50","doi-asserted-by":"publisher","unstructured":"Role, F., Meyer, S., Amblard, V.: Fill the Gap: quantifying and reducing the modality gap in image-text representation learning (2025). https:\/\/doi.org\/10.48550\/ARXIV.2505.03703. Accessed 12 Apr 2025","DOI":"10.48550\/ARXIV.2505.03703"},{"key":"23_CR51","doi-asserted-by":"publisher","unstructured":"Saijo, K., Ebbers, J., Germain, F.G., Khurana, S., Wiehern, G., Roux, J.L.: Leveraging audio-only data for text-queried target sound extraction. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, pp.\u00a01\u20135. IEEE (2025). https:\/\/doi.org\/10.1109\/icassp49660.2025.10888769","DOI":"10.1109\/icassp49660.2025.10888769"},{"key":"23_CR52","unstructured":"Saitis, C., Siedenburg, K.: When ChatGPT talks timbre. In: Proceedings of the Third International Conference on Timbre, pp. 73\u201377. The School of Music Studies Aristotle University of Thessaloniki, Aristotle University of Thessaloniki (2023)"},{"key":"23_CR53","doi-asserted-by":"publisher","unstructured":"Saitis, C., Weinzierl, S.: The semantics of timbre. In: Siedenburg, K., Saitis, C., McAdams, S., Popper, A.N., Fay, R.R. (eds.) Timbre: Acoustics, Perception, and Cognition, vol.\u00a069, pp. 119\u2013149. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-14832-4_5","DOI":"10.1007\/978-3-030-14832-4_5"},{"issue":"1","key":"23_CR54","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/MPOT.2016.2550015","volume":"37","author":"J Salas","year":"2018","unstructured":"Salas, J.: Generating music from literature using topic extraction and sentiment analysis. IEEE Potentials 37(1), 15\u201318 (2018). https:\/\/doi.org\/10.1109\/MPOT.2016.2550015","journal-title":"IEEE Potentials"},{"key":"23_CR55","doi-asserted-by":"publisher","unstructured":"Seetharaman, P., Pardo, B.: Audealize: crowdsourced audio production tools. J. Audio Eng. Soc. 64(9), 683\u2013695 (2016). https:\/\/doi.org\/10.17743\/jaes.2016.0037","DOI":"10.17743\/jaes.2016.0037"},{"key":"23_CR56","unstructured":"Shi, P., Welle, M.C., Bj\u00f6rkman, M., Kragic, D.: Towards understanding the modality gap in CLIP. In: ICLR 2023 Workshop on Multimodal Representation Learning: Perks and Pitfalls (2023). https:\/\/openreview.net\/forum?id=8W3KGzw7fNI, last accessed 2025\/10\/27"},{"issue":"1","key":"23_CR57","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1080\/09298215.2015.1132737","volume":"45","author":"K Siedenburg","year":"2016","unstructured":"Siedenburg, K., Fujinaga, I., McAdams, S.: A comparison of approaches to timbre descriptors in music information retrieval and music psychology. J. New Music Res. 45(1), 27\u201341 (2016). https:\/\/doi.org\/10.1080\/09298215.2015.1132737","journal-title":"J. New Music Res."},{"key":"23_CR58","doi-asserted-by":"publisher","unstructured":"Siedenburg, K., Saitis, C.: The language of sounds unheard: exploring musical timbre semantics of large language models (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.07830. Accessed 20 Jul 2025","DOI":"10.48550\/arXiv.2304.07830"},{"key":"23_CR59","doi-asserted-by":"publisher","unstructured":"Song, H., Dong, L., Zhang, W., Liu, T., Wei, F.: CLIP models are few-shot learners: empirical studies on VQA and visual entailment. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.421","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"23_CR60","unstructured":"Tam, D., Raffel, C., Bansal, M.: Simple weakly-supervised image captioning via CLIP\u2019s multimodal embeddings. In: The AAAI-23 Workshop on Creative AI Across Modalities (2023). https:\/\/openreview.net\/forum?id=UMxeP-FuwyC. Accessed 21 Jul 2025"},{"key":"23_CR61","doi-asserted-by":"publisher","unstructured":"Thompson, A.E.: Playing Tag: An Analysis of Vocabulary Patterns and Relationships Within a Popular Music Folksonomy. Master\u2019s thesis, University of North Carolina at Chapel Hill (2008). https:\/\/doi.org\/10.17615\/08PE-W163","DOI":"10.17615\/08PE-W163"},{"key":"23_CR62","doi-asserted-by":"publisher","unstructured":"Tian, H., Lattner, S., Saitis, C.: Assessing the alignment of audio representations with timbre similarity ratings (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.07764, ISMIR 2025. Accessed 24 Sept 2025","DOI":"10.48550\/arXiv.2507.07764"},{"key":"23_CR63","unstructured":"Udandarao, V.: Understanding and Fixing the Modality Gap in Vision-Language Models. Master\u2019s thesis, University of Cambridge (2022)"},{"key":"23_CR64","doi-asserted-by":"publisher","unstructured":"Vaillant, G.L., Molle, Y.: Contrastive timbre representations for musical instrument and synthesizer retrieval (2025). https:\/\/doi.org\/10.48550\/arXiv.2509.13285. Accessed 24 Sept 2025","DOI":"10.48550\/arXiv.2509.13285"},{"key":"23_CR65","unstructured":"Velissaridis, G., Athwal, R., Musharaf, M., Fazekas, G., Saitis, C.: Evaluating foundation models on timbre-related cognitive tasks. In: 1st Workshop on Large Language Models for Music & Audio (LLM4MA) (2025). https:\/\/openreview.net\/forum?id=tXyh8CY9kZ. Accessed 27 Oct 2025"},{"key":"23_CR66","doi-asserted-by":"publisher","first-page":"205920431984661","DOI":"10.1177\/2059204319846617","volume":"2","author":"Z Wallmark","year":"2019","unstructured":"Wallmark, Z.: Semantic crosstalk in timbre perception. Music Sci. 2, 205920431984661 (2019). https:\/\/doi.org\/10.1177\/2059204319846617","journal-title":"Music Sci."},{"key":"23_CR67","doi-asserted-by":"publisher","unstructured":"Wang, E., Peng, Z., Xie, Z., Yang, F., Liu, X., Cheng, M.M.: GET: unlocking the multi-modal potential of CLIP for generalized category discovery. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pp. 20296\u201320306. arXiv (2025). https:\/\/doi.org\/10.48550\/arXiv.2403.09974, CVPR 2025. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2403.09974"},{"key":"23_CR68","doi-asserted-by":"publisher","unstructured":"Wang, J., Zhang, Y., Yan, M., Zhang, J., Sang, J.: Zero-shot image captioning by anchor-augmented vision-language space alignment (2022). https:\/\/doi.org\/10.48550\/arXiv.2211.07275. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2211.07275"},{"key":"23_CR69","doi-asserted-by":"publisher","unstructured":"Wang, Y., Luo, H., Xu, J., Sun, Y., Wang, F.: Text data-centric image captioning with interactive prompts (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.19193. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2403.19193"},{"key":"23_CR70","doi-asserted-by":"publisher","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, pp.\u00a01\u20135. IEEE (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095969","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Yi, C., He, Y.H., Zhan, D.C., Ye, H.J.: Bridge the modality and capability gaps in vision-language model selection. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems. vol.\u00a037, pp. 34429\u201334452. Curran Associates, Inc. (2024)","DOI":"10.52202\/079017-1085"},{"key":"23_CR72","doi-asserted-by":"publisher","unstructured":"Yu, Y., et al.: Multimodal knowledge alignment with reinforcement learning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2023). https:\/\/doi.org\/10.48550\/arXiv.2205.12630. Accessed 30 Jun 2025","DOI":"10.48550\/arXiv.2205.12630"},{"key":"23_CR73","doi-asserted-by":"publisher","unstructured":"Zeng, D., Shen, Y., Lin, M., Yi, Z., Ouyang, J.: Zero-shot image captioning with multi-type entity representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 21, pp. 22308\u201322316 (2025). https:\/\/doi.org\/10.1609\/aaai.v39i21.34386, number: 21","DOI":"10.1609\/aaai.v39i21.34386"},{"key":"23_CR74","doi-asserted-by":"publisher","unstructured":"Zeng, Z., Xie, Y., Zhang, H., Chen, C., Chen, B., Wang, Z.: MeaCap: memory-augmented zero-shot image captioning. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14100\u201314110 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01337, ISSN: 2575-7075","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"23_CR75","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TASLPRO.2025.3567770","volume":"33","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Xu, X., Du, R., Liu, H., Dong, Y., Tan, Z.H., Wang, W., Ma, Z.: Zero-shot audio captioning using soft and hard prompts. IEEE Trans. Audio Speech Lang. Process. 33, 2045\u20132058 (2025). https:\/\/doi.org\/10.1109\/TASLPRO.2025.3567770","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"23_CR76","unstructured":"Zhang, Y., HaoChen, J.Z., Huang, S.C., Wang, K.C., Zou, J., Yeung, S.: Diagnosing and rectifying vision models using language. In: The Eleventh International Conference on Learning Representations (ICLR) (2023). https:\/\/openreview.net\/forum?id=D-zfUK7BR6c. Accessed 30 Jun 2025"},{"key":"23_CR77","unstructured":"Zhang, Y., Sui, E., Yeung, S.: Connect, collapse, corrupt: learning cross-modal tasks with UNI-modal data. In: The Twelfth International Conference on Learning Representations (ICLR) (2023). https:\/\/openreview.net\/forum?id=ttXg3SKAg5. Accessed 09 Jul 2025"},{"key":"23_CR78","doi-asserted-by":"publisher","unstructured":"Zhao, P., Luan, R., Zhang, W., Wu, P., He, S.: Guiding cross-modal representations with MLLM priors via preference alignment (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.06970. Accessed 26 Jun 2025","DOI":"10.48550\/arXiv.2506.06970"},{"key":"23_CR79","doi-asserted-by":"publisher","unstructured":"Zhou, Y., et al.: Towards language-free training for text-to-image generation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 17886\u201317896. IEEE (2022). https:\/\/doi.org\/10.1109\/cvpr52688.2022.01738","DOI":"10.1109\/cvpr52688.2022.01738"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-24350-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:26:00Z","timestamp":1777433160000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-24350-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032243492","9783032243508"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-24350-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toulouse","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"8 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2026\/evomusart\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}