%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:11:08 PM

@INPROCEEDINGS{Juan_SLT2023_2023,
         author = {Zuluaga-Gomez, Juan and Sarfjoo, Seyyed Saeed and Prasad, Amrutha and Iuliia, Nigmatulina and Motlicek, Petr and Ond{\v r}ej, Karel and Ohneiser, Oliver},
       keywords = {air traffic control communications, chunking, Speaker change detection, speaker role detection, Text-based speaker diarization},
       projects = {Idiap, HAAWAII, EC H2020- ATCO2},
          month = jan,
          title = {BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications},
      booktitle = {2023 IEEE Spoken Language Technology Workshop (SLT)},
         series = {1},
         volume = {1},
         number = {1},
           year = {2023},
   organization = {IEEE},
            url = {https://arxiv.org/abs/2110.05781},
       abstract = {Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common challenge is speech activity detection (SAD) and speaker diarization (SD). In the failure condition, two or more segments remain in the same recording, jeopardizing the overall performance. We propose a system that combines SAD and a BERT model to perform speaker change detection and speaker role detection (SRD) by chunking ASR transcripts, i.e., SD with a defined number of speakers together with SRD. The proposed model is evaluated on real-life public ATC databases. Our BERT SD model baseline reaches up to 10\% and 20\% token-based Jaccard error rate (JER) in public and private ATC databases. We also achieved relative improvements of 32\% and 7.7\% in JERs and SD error rate (DER), respectively, compared to VBx, a well-known SD system.},
            pdf = {https://publications.idiap.ch/attachments/papers/2022/Juan_SLT2023_2023.pdf}
}