{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:31:26Z","timestamp":1742999486076,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-78014-1_24","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:24:15Z","timestamp":1732191855000},"page":"326-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Conformer LLM \u2013 Convolution Augmented Large Language Models"],"prefix":"10.1007","author":[{"given":"Prateek","family":"Verma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"24_CR1","unstructured":"Abadi\u00a0et. al, M.: $$\\{$$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":"24_CR2","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. CoRR abs\/1609.08144 (2016). http:\/\/arxiv.org\/abs\/1609.08144"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Al-Rfou, R., Choe, D., Constant, N., Guo, M., Jones, L.: Character-level language modeling with deeper self-attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 3159\u20133166 (2019)","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"24_CR4","unstructured":"Brown, T.B., et\u00a0al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"24_CR5","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. Adv. Neural. Inf. Process. Syst. 34, 15084\u201315097 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR6","unstructured":"Chen, M., et\u00a0al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"key":"24_CR7","unstructured":"Dosovitskiy, A., Beyer, L., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR8","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"24_CR9","unstructured":"Glaese, A., et al.: Improving alignment of dialogue agents via targeted human judgements. arXiv preprint arXiv:2209.14375 (2022)"},{"key":"24_CR10","unstructured":"Goel, K., Gu, A., Donahue, C., R\u00e9, C.: It\u2019s raw! audio generation with state-space models. arXiv preprint arXiv:2202.09729 (2022)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Gulati, A., et\u00a0al.: Conformer: convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Haque, A., Guo, M., Verma, P., Fei-Fei, L.: Audio-linguistic embeddings for spoken sentences. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7355\u20137359. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682553"},{"key":"24_CR13","unstructured":"Kalchbrenner, N., Espeholt, L., Simonyan, K., Oord, A.V.D., Graves, A., Kavukcuoglu, K.: Neural machine translation in linear time. arXiv preprint arXiv:1610.10099 (2016)"},{"key":"24_CR14","unstructured":"Lewkowycz, A., et\u00a0al.: Solving quantitative reasoning problems with language models. arXiv preprint arXiv:2206.14858 (2022)"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Madani, A., et al.: Progen: language modeling for protein generation. arXiv preprint arXiv:2004.03497 (2020)","DOI":"10.1101\/2020.03.07.982272"},{"key":"24_CR16","unstructured":"Oord, A.V.D., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Vinyals, O., Senior, A., Sak, H.: Convolutional, long short-term memory, fully connected deep neural networks. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4580\u20134584. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"24_CR19","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning, pp. 785\u2013799. PMLR (2023)"},{"key":"24_CR20","first-page":"5492","volume":"33","author":"A Tamkin","year":"2020","unstructured":"Tamkin, A., Jurafsky, D., Goodman, N.: Language through a prism: a spectral approach for multiscale language representations. Adv. Neural. Inf. Process. Syst. 33, 5492\u20135504 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR21","unstructured":"the Test\u00a0Data, A.: Matt mahoney (Sept 1, 2011). Accessed 1 Jul 2023"},{"key":"24_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"24_CR23","unstructured":"Verma, P.: Goodbye wavenet\u2013a language model for raw audio with context of 1\/2 million samples. arXiv preprint arXiv:2206.08297 (2022)"},{"key":"24_CR24","unstructured":"Verma, P., Berger, J.: Audio transformers: transformer architectures for large scale audio understanding. adieu convolutions. arXiv preprint arXiv:2105.00335 (2021)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Verma, P., Chafe, C.: A generative model for raw audio using transformer architectures. In: 2021 24th International Conference on Digital Audio Effects (DAFx), pp. 230\u2013237. IEEE (2021)","DOI":"10.23919\/DAFx51585.2021.9768298"},{"key":"24_CR26","unstructured":"Verma, P., Smith, J.: A framework for contrastive and generative learning of audio representations. arXiv preprint arXiv:2010.11459 (2020)"},{"key":"24_CR27","unstructured":"Wei, J., Tay, Y., et\u00a0al.: Emergent abilities of large language models. Trans. Mach. Learn. Res"},{"key":"24_CR28","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903 (2022)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Wu, H., : CVT: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"24_CR30","unstructured":"Zeng, A., et al.: Socratic models: composing zero-shot multimodal reasoning with language. arXiv preprint arXiv:2204.00598 (2022)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:08:10Z","timestamp":1736348890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}