Speaker detection in the wild: Lessons learned from JSALT 2019 - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Speaker detection in the wild: Lessons learned from JSALT 2019

Ling Guo
  • Function : Author
Koji Okabe
  • Function : Author
Saurabh Kataria
  • Function : Author
  • PersonId : 891812


This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tackle a wide range of conditions that go from meetings to wild speech. We describe the research threads we explored and a set of modules that was successful for these scenarios. The ultimate goal was to explore speaker detection; but our first finding was that an effective diarization improves detection, and not having a diarization stage impoverishes the performance. All the different configurations of our research agree on this fact and follow a main backbone that includes diarization as a previous stage. With this backbone, we analyzed the following problems: voice activity detection, how to deal with noisy signals, domain mismatch, how to improve the clustering; and the overall impact of previous stages in the final speaker detection. In this paper, we show partial results for speaker diarizarion to have a better understanding of the problem and we present the final results for speaker detection.
Fichier principal
Vignette du fichier
1912.00938.pdf (410.95 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02417632 , version 1 (20-12-2019)



Paola García, Jesus Villalba, Hervé Bredin, Jun Du, Diego Castan, et al.. Speaker detection in the wild: Lessons learned from JSALT 2019. Odyssey 2020 The Speaker and Language Recognition Workshop, Nov 2020, Tokyo, Japan. ⟨hal-02417632⟩
352 View
99 Download



Gmail Facebook X LinkedIn More