%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 05:48:43 PM

@INPROCEEDINGS{Kumar_EMNLP2024_2024,
         author = {Kumar, Shashi and Madikeri, Srikanth and Zuluaga-Gomez, Juan and Thorbecke, Iuliia and Villatoro-Tello, Esa{\'{u}} and Burdisso, Sergio and Motlicek, Petr and S, Karthik Pandia D and Ganapathiraju, Aravind},
       keywords = {multitask training, named entity recognition, Speaker change detection, speech recognition, XLSR-Transducer},
       projects = {UNIPHORE, ELOQUENCE},
          month = nov,
          title = {TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR},
      booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
           year = {2024},
          pages = {20988–20995},
      publisher = {Association for Computational Linguistics (ACL)},
        address = {Miami, Florida, USA},
            url = {https://aclanthology.org/2024.emnlp-main.1167},
       crossref = {Kumar_Idiap-RR-07-2024},
       abstract = {In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for tasks like semantic endpointing and named entity recognition (NER). Our paper introduces TokenVerse, a single Transducer-based model designed to handle multiple tasks. This is achieved by integrating task-specific tokens into the reference text during ASR model training, streamlining the inference and eliminating the need for separate NLP models. In addition to ASR, we conduct experiments on 3 different tasks: speaker change detection, endpointing, and NER. Our experiments on a public and a private dataset show that the proposed method improves ASR by up to 7.7\% in relative WER while outperforming the cascaded pipeline approach in individual task performance. Our code is publicly available: https://github.com/idiap/tokenverse-unifying-speech-nlp},
            pdf = {https://publications.idiap.ch/attachments/papers/2024/Kumar_EMNLP2024_2024.pdf}
}



crossreferenced publications: 
@TECHREPORT{Kumar_Idiap-RR-07-2024,
         author = {Kumar, Shashi and Madikeri, Srikanth and Zuluaga-Gomez, Juan and Iuliia, Nigmatulina and Villatoro-Tello, Esa{\'{u}} and Burdisso, Sergio and Motlicek, Petr and S, Karthik Pandia D and Ganapathiraju, Aravind},
       keywords = {multitask training, named entity recognition, Speaker change detection, speech recognition, XLSR-Transducer},
       projects = {UNIPHORE},
          month = {8},
          title = {TokenVerse: Unifying Speech and NLP Tasks via Transducer-based ASR},
           type = {Idiap-RR},
         number = {Idiap-RR-07-2024},
           year = {2024},
    institution = {Idiap},
            url = {https://arxiv.org/abs/2407.04444},
       abstract = {In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for tasks like semantic endpointing and named entity recognition (NER). Our paper introduces TokenVerse, a single Transducer-based model designed to handle multiple tasks. This is achieved by integrating task-specific tokens into the reference text during ASR model training, streamlining the inference and eliminating the need for separate NLP models. In addition to ASR, we conduct experiments on 3 different tasks: speaker change detection, endpointing, and NER. Our experiments on a public and a private dataset show that the proposed method improves ASR by up to 7.7\% in relative WER while outperforming the cascaded pipeline approach in individual task performance. Additionally, we present task transfer learning to a new task within an existing TokenVerse.},
            pdf = {https://publications.idiap.ch/attachments/reports/2024/Kumar_Idiap-RR-07-2024.pdf}
}