Picture for Ladislav Mosner

Ladislav Mosner

Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing

Nov 03, 2022
Sofoklis Kakouros, Themos Stafylakis, Ladislav Mosner, Lukas Burget

Figure 1 for Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing

Figure 2 for Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing

Figure 3 for Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing

Figure 4 for Speech-based emotion recognition with self-supervised models using attentive channel-wise correlations and label smoothing

* Submitted to IEEE-ICASSP 2023

Access Paper or Ask Questions

Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch

Mar 19, 2022
Anna Silnova, Themos Stafylakis, Ladislav Mosner, Oldrich Plchot, Johan Rohdin, Pavel Matejka, Lukas Burget, Ondrej Glembek, Niko Brummer

Figure 1 for Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch

Figure 2 for Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch

Figure 3 for Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch

Figure 4 for Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch

* Submitted to Odyssey 2022, under review

Access Paper or Ask Questions