%Aigaion2 BibTeX export from Idiap Publications
%Saturday 16 November 2024 10:20:21 AM

@INPROCEEDINGS{Sarfjoo_INTERSPEECH_2021,
         author = {Sarfjoo, Seyyed Saeed and Madikeri, Srikanth and Motlicek, Petr},
       keywords = {logistic regression, multi-lingual automatic speech recognition, multi-lingual SAD, Speech activity detection},
       projects = {EC H2020-ROXANNE, Idiap},
          title = {Speech Activity Detection Based on Multilingual Speech Recognition System},
      booktitle = {Interspeech},
           year = {2021},
       abstract = {To better model the contextual information and increase the generalization ability of Speech Activity Detection (SAD) system, this paper leverages a multi-lingual Automatic Speech Recognition (ASR) system to perform SAD. Sequence-discriminative training of Acoustic Model (AM) using Lattice-Free Maximum Mutual Information (LF-MMI) loss function, effectively extracts the contextual information of the input acoustic frame. Multi-lingual AM training, causes the robustness to noise and language variabilities. The index of maximum output posterior is considered as a frame-level speech/non-speech decision function. Majority voting and logistic regression are applied to fuse the language-dependent decisions. The multi-lingual ASR is trained on 18 languages of BABEL datasets and the built SAD is evaluated on 3 different languages. On out-of-domain datasets, the proposed SAD model shows significantly better performance with respect to baseline models. On the Ester2 dataset, without using any in-domain data, this model outperforms the WebRTC, phoneme recognizer based VAD (Phn Rec), and Pyannote baselines (respectively by 7.1, 1.7, and 2.7\% absolute) in Detection Error Rate (DetER) metrics. Similarly, on the LiveATC dataset, this model outperforms the WebRTC, Phn Rec, and Pyannote baselines (respectively by 6.4, 10.0, and 3.7\% absolutely) in DetER metrics.},
            pdf = {https://publications.idiap.ch/attachments/papers/2021/Sarfjoo_INTERSPEECH_2021.pdf}
}