Piotr Masztalski

4 papers · 2020–2025 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze

Venues

Interspeech (4)

Top co-authors

Mateusz Matuszewski (3) Michal Romaniuk (2) Karol Piaskowski (2) Jakub Żak (1) Bartłomiej Zgórzyński (1) Juliusz Wójtowicz-Kruk (1) Michał Romaniuk (1) Konrad Kowalczyk (1) Władysław Średniawa (1)

Research topics

Speech & Audio (3) Deep Learning (2) Learning Types (2) Synthesis (2) Artificial Intelligence (1) Machine Learning (1) Application Areas (1) Core AI (1) Recognition (1)

Keywords

speech enhancement (2) supervised contrastive learning (1) deep learning (1) speaker embedding (1) speaker verification (1) mobile device (1) stochastic modeling (1) low latency (1) multi-encoder architecture (1) hard negative sampling (1) speech emotion recognition (1) room impulse response (1) acoustic parameter (1) audio data augmentation (1) fusion module (1) stochastic generation (1) complex-valued ratio mask (1) batch composition (1) categorical emotion classification (1) multi-task learning (1)

Papers

Clustering-based Hard Negative Sampling for Supervised Contrastive Speaker Verification Interspeech 2025 Multi-task learning for speech emotion recognition in naturalistic conditions Interspeech 2025 Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networks Interspeech 2020 StoRIR: Stochastic Room Impulse Response Generation for Audio Data Augmentation Interspeech 2020