{
    "ok": true,
    "doi": "10.46243/jst.2025.v10.i01.pp10-25",
    "references_in_record": 27,
    "not_read": [],
    "own_doi": [],
    "total": 24,
    "page": 1,
    "pages": 2,
    "per_page": 20,
    "items": [
        {
            "position": 1,
            "key": "ref1",
            "doi": "10.1109/tasl.2011.2125954",
            "doi_url": "https://doi.org/10.1109/tasl.2011.2125954",
            "unstructured": "Anguera X, Bozonnet S, Evans N, Fredouille C, Friedland G, Vinyals O. Speaker diarization: A review of recent research. IEEE Transactions on Audio, Speech, and Language Processing. 2012;20(2):356-370. doi:10.1109/ TASL.2011.2125954",
            "held": false
        },
        {
            "position": 2,
            "key": "ref2",
            "doi": "10.21437/interspeech.2020-3039",
            "doi_url": "https://doi.org/10.21437/interspeech.2020-3039",
            "unstructured": "Mao HH, Li S, McAuley J, Cottrell G. Speech recognition and multi-speaker diarization of long conversations. arXiv preprint. 2020;arXiv:2005.08072",
            "held": false
        },
        {
            "position": 3,
            "key": "ref3",
            "doi": "10.1080/10810730.2024.2321385",
            "doi_url": "https://doi.org/10.1080/10810730.2024.2321385",
            "unstructured": "Frølund, J., Løkke, A., Jensen, H., & Farver-Vestergaard, I. (2024). Development of Podcasts in a Hospital Setting: A User-Centered Approach. Journal of Health Communication, 29(4), 244–",
            "held": false
        },
        {
            "position": 4,
            "key": "ref4",
            "doi": "10.1080/10810730.2024.2321385",
            "doi_url": "https://doi.org/10.1080/10810730.2024.2321385",
            "unstructured": "https://doi.org/10.1080/10810730.2024. 2321385",
            "held": false
        },
        {
            "position": 5,
            "key": "ref5",
            "doi": "10.1109/tmm.2012.2233724",
            "doi_url": "https://doi.org/10.1109/tmm.2012.2233724",
            "unstructured": "Vallet F, Essid S, Carrive J. A multimodal approach to speaker diarization on TV talk-shows. IEEE Transactions on Multimedia. 2013;15(3):509-",
            "held": false
        },
        {
            "position": 6,
            "key": "ref6",
            "doi": "10.1109/tmm.2012.2233724",
            "doi_url": "https://doi.org/10.1109/tmm.2012.2233724",
            "unstructured": "doi:10.1109/TMM.2012.2233724",
            "held": false
        },
        {
            "position": 7,
            "key": "ref7",
            "doi": "10.1145/3643834.3661591",
            "doi_url": "https://doi.org/10.1145/3643834.3661591",
            "unstructured": "Wang S, Ning Z, Truong A, et al. PodReels: Human-AI co-creation of video podcast teasers. Proceedings of the 2024 Designing Interactive Systems Conference (DIS ’24). ACM. 2024;17 pages. doi:10.1145/3643834.3661591",
            "held": false
        },
        {
            "position": 8,
            "key": "ref8",
            "doi": "10.1145/3626767.3625304",
            "doi_url": "https://doi.org/10.1145/3626767.3625304",
            "unstructured": "Austin A, Samuel A. Enhancing podcasting by leveraging AI technologies. Communications of the ACM. 2023;66(10):48-55. doi:10.1145/3626767.3625304",
            "held": false
        },
        {
            "position": 10,
            "key": "ref10",
            "doi": "10.1016/j.specom.2009.08.009",
            "doi_url": "https://doi.org/10.1016/j.specom.2009.08.009",
            "unstructured": "Kinnunen T, Li H. An overview of textindependent speaker recognition: From features to supervectors. Speech Communication. 2010;52(1):12-40. doi:10.1016/j. specom.2009.08.009",
            "held": false
        },
        {
            "position": 11,
            "key": "ref11",
            "doi": "10.1177/1461444820963776",
            "doi_url": "https://doi.org/10.1177/1461444820963776",
            "unstructured": "Chan-Olmsted, S., & Wang, R. (2022). Understanding podcast users: Consumption motives and behaviors. New Media & Society, 24(3), 684-704. https://doi. org/10.1177/1461444820963776",
            "held": false
        },
        {
            "position": 12,
            "key": "ref12",
            "doi": "10.1145/3173574.3174214",
            "doi_url": "https://doi.org/10.1145/3173574.3174214",
            "unstructured": "Martin Porcheron, Joel E. Fischer, Stuart Reeves, and Sarah Sharples. 2018. Voice Interfaces in Everyday Life. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ‘18). Association for Computing Machinery, New York, NY, USA, Paper 640, 1–12. https://doi.org/10.1145/3173574.3174214",
            "held": false
        },
        {
            "position": 13,
            "key": "ref13",
            "doi": "10.1145/3591106.3592270",
            "doi_url": "https://doi.org/10.1145/3591106.3592270",
            "unstructured": "Iacopo Ghinassi, Lin Wang, Chris Newell, and Matthew Purver. 2023. Multimodal Topic Segmentation of Podcast Shows with Pre-trained Neural Encoders. In Proceedings of the 2023 ACM International Conference on Multimedia Retrieval (ICMR ‘23). Association for Computing Machinery, New York, NY, USA, 602–606. https://doi.org/10.1145/3591106.3592270",
            "held": false
        },
        {
            "position": 14,
            "key": "ref14",
            "doi": "10.1109/ijcnn55064.2022.9892054",
            "doi_url": "https://doi.org/10.1109/ijcnn55064.2022.9892054",
            "unstructured": "A. Hajavi and A. Etemad, “Fine-grained Early Frequency Attention for Deep Speaker Recognition,” 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 2022, pp. 1-6, doi: 10.1109/ IJCNN55064.2022.9892054",
            "held": false
        },
        {
            "position": 15,
            "key": "ref15",
            "doi": "10.1109/icpwc.2005.1431364",
            "doi_url": "https://doi.org/10.1109/icpwc.2005.1431364",
            "unstructured": "U. S. Jha, “Efficient multimodal signal processing engine ease communication, computing, and multimedia convergence,” 2005 IEEE International Conference on Personal Wireless Communications, 2005. ICPWC 2005., New Delhi, India, 2005, pp. 348-352, doi: 10.1109/ ICPWC.2005.1431364",
            "held": false
        },
        {
            "position": 16,
            "key": "ref16",
            "doi": "10.3390/metrics1010002",
            "doi_url": "https://doi.org/10.3390/metrics1010002",
            "unstructured": "Galli, Carlo, et al. “Topic Modeling for Faster Literature Screening Using Transformer-Based Embeddings.” Metrics. Vol. 1. No 1. MDPI, 2024",
            "held": false
        },
        {
            "position": 17,
            "key": "ref17",
            "doi": "10.1109/tsa.2002.804546",
            "doi_url": "https://doi.org/10.1109/tsa.2002.804546",
            "unstructured": "Lie Lu, Hong-Jiang Zhang and Hao Jiang, “Content analysis for audio classification and segmentation,” in IEEE Transactions on Speech and Audio Processing, vol. 10, no. 7, pp. 504- 516, Oct. 2002, doi: 10.1109/TSA.2002.804546",
            "held": false
        },
        {
            "position": 18,
            "key": "ref18",
            "doi": "10.1109/access.2022.3177584",
            "doi_url": "https://doi.org/10.1109/access.2022.3177584",
            "unstructured": "A. Gomez, M. S. Pattichis and S. Celedón-Pattichis, “Speaker Diarization and Identification From Single Channel Classroom Audio Recordings Using Virtual Microphones,” in IEEE Access, vol. 10, pp. 56256-56266, 2022, doi: 10.1109/ACCESS.2022.3177584",
            "held": false
        },
        {
            "position": 19,
            "key": "ref19",
            "doi": "10.1007/978-3-031-47718-8_7",
            "doi_url": "https://doi.org/10.1007/978-3-031-47718-8_7",
            "unstructured": "Ghosh, R. et al. (2024). Topic Segmentation of Semi-structured and Unstructured Conversational Datasets Using Language Models. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2023. Lecture Notes in Networks and Systems, vol 825. Springer, Cham. https://doi.org/10.1007/978-3-031- 47718-8_7",
            "held": false
        },
        {
            "position": 20,
            "key": "ref20",
            "doi": "10.1145/3209811.3209875",
            "doi_url": "https://doi.org/10.1145/3209811.3209875",
            "unstructured": "Deepika Yadav, Mayank Gupta, Malolan Chetlur, and Pushpendra Singh. 2018. Automatic Annotation of Voice Forum Content for Rural Users and Evaluation of Relevance. In Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS ‘18). Association for Computing Machinery, New York, NY, USA, Article 12, 1–11. https://doi.org/10.1145/3209811.3209875",
            "held": false
        },
        {
            "position": 21,
            "key": "ref21",
            "doi": "10.1109/icassp39728.2021.9414315",
            "doi_url": "https://doi.org/10.1109/icassp39728.2021.9414315",
            "unstructured": "F. Landini et al., “Analysis of the but Diarization System for Voxconverse Challenge,” ICASSP Waseem Syed: Revolutionizing Audio Content Navigation: AI-Enhanced Multimodality and Machine Learning for Speaker Diarization and Topic Segmentation 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada, 2021, pp. 5819-5823, doi: 10.1109/ICASSP39728.2021.9414315",
            "held": false
        }
    ]
}