%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 12:32:04 PM

@ARTICLE{Khalil_AEROSPACE_2023,
         author = {Khalil, Driss and Prasad, Amrutha and Motlicek, Petr and Juan, Zuluaga-Gomez. and Iuliia, Nigmatulina and Madikeri, Srikanth and Christof, Sch{\"{u}}pbach},
       keywords = {speaker clustering, speaker role detection},
       projects = {Idiap, armasuisse},
          month = sep,
          title = {An Automatic Speaker Clustering Pipeline for the Air Traffic Communication Domain},
        journal = {Aerospace},
         volume = {10},
         number = {10},
           year = {2023},
          pages = {876},
            url = {https://www.mdpi.com/2226-4310/10/10/876},
            doi = {https://doi.org/10.3390/aerospace10100876},
       abstract = {In air traffic management (ATM), voice communications are critical for ensuring the safe and efficient operation of aircraft. The pertinent voice communications—air traffic controller (ATCo) and pilot—are usually transmitted in a single channel, which poses a challenge when developing automatic systems for air traffic management. Speaker clustering is one of the challenges when applying speech processing algorithms to identify and group the same speaker among different speakers. We propose a pipeline that deploys (i) speech activity detection (SAD) to identify speech segments, (ii) an automatic speech recognition system to generate the text for audio segments, (iii) text-based speaker role classification to detect the role of the speaker—ATCo or pilot in our case—and (iv) unsupervised speaker clustering to create a cluster of each individual pilot speaker from the obtained speech utterances. The speech segments obtained by SAD are input into an automatic speech recognition (ASR) engine to generate the automatic English transcripts. The speaker role classification system takes the transcript as input and uses it to determine whether the speech was from the ATCo or the pilot. As the main goal of this project is to group the speakers in pilot communication, only pilot data acquired from the classification system is employed. We present a method for separating the speech parts of pilots into different clusters based on the speaker’s voice using agglomerative hierarchical clustering (AHC). The performance of the speaker role classification and speaker clustering is evaluated on two publicly available datasets: the ATCO2 corpus and the Linguistic Data Consortium Air Traffic Control Corpus (LDC-ATCC). Since the pilots’ real identities are unknown, the ground truth is generated based on logical hypotheses regarding the creation of each dataset, timing information, and the information extracted from associated callsigns. In the case of speaker clustering, the proposed algorithm achieves an accuracy of 70\% on the LDC-ATCC dataset and 50\% on the more noisy ATCO2 dataset.},
            pdf = {https://publications.idiap.ch/attachments/papers/2023/Khalil_AEROSPACE_2023.pdf}
}