Impact of overlapping speech detection on speaker diarization for broadcast news and debates

Abstract

The overlapping speech detection systems developped by Orange and LIMSI for the ETAPE evaluation campaign on French broadcast news and debates are described. Using either cepstral features or a multi-pitch analysis, a F1-measure for overlapping speech detection up to 59.2% is reported on the TV data of the ETAPE evaluation set, where 6.7% of the speech was measured as overlapping, ranging from 1.2% in the news to 10.7% in the debates. Overlapping speech segments were excluded during the speaker diarization stage, and these segments were further labelled with the two nearest speaker labels, taking into account the temporal distance. We describe the effects of this strategy for various overlapping speech systems and we show that it improves the diarization error rate in all situations and up to 26.1% relative in our best configuration.

Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection

“…https://github.com/jsalt2019-diadet/jsalt2019-diadet3 Thanks to Claude Barras for providing the overlapped speech detection output corresponding to system L 1 inTable 2of[20], and Marie Kunešová for providing the overlapped speech detection output corresponding to system "AMI test (all subsets) + dereverberation" inTable 2of[8].…”

Pyannote.Audio: Neural Building Blocks for Speaker Diarization

“…pyannote.audio provides a set of command line tools for training, validation, and application of modules listed in 1 x-vector aficionados would still suggest to use PLDA anyway... Table 3. Evaluation of pre-trained overlapped speech detection models, in terms of precision (%) and recall (%).…”

“…Among all pyannote.audio alternatives, it is the most similar: written in Python, it provides most of the afore-This research was partly funded by the French National Research Agency (ANR) through the ODESSA (ANR-15-CE39-0010) and PLUM-COT (ANR-16-CE92-0025) projects. We would like to thank Claude Barras for providing the overlapped speech detection output corresponding to system L 1 in Table 2 of [1], Neville Ryant for the speaker diarization output of the winning submission to DIHARD 2019 [2,3], Marie Kunešová for the overlapped speech detection output corresponding to system "AMI test (all subsets) + dereverberation" in Table 2 of [4], and Sylvain Meignier for the speaker diarization output of [5] on ETAPE dataset. mentioned blocks, and goes all the way down to the actual evaluation of the system.…”

Target Speaker Extraction for Multi-Talker Speaker Verification

“…Speaker diarization can be useful for speaker verification with nonoverlapping multi-talker speech [1][2][3][4][5][6]. It can effectively exclude unwanted speech segments when the speakers only slightly overlap [7,8]. However, such system fails when multitalkers speak simultaneously most of the time.…”