Kateřina Žmolíková

Computer Science · Physical Sciences

13h-index1.2kcitations40works0.82yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(33), Speech and Audio Processing(27), Music and Audio Processing(20), Natural Language Processing Techniques(4), Emotion and Mood Recognition(2)

Publications40 total

GSRM: Generative Speech Reward Model for Speech RLHF
arXiv (Cornell University)·2026Open Access
GSRM: Generative Speech Reward Model for Speech RLHF
ArXiv.org·2026Open Access
Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
2025· 1 cited
Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
arXiv (Cornell University)·2024Open Access
Analysis and interpretation of joint source separation and sound event detection in domestic environments
PLoS ONE·2024· 3 citedOpen Access
Masked Spectrogram Prediction for Unsupervised Domain Adaptation in Speech Enhancement
IEEE Open Journal of Signal Processing·2023· 4 citedOpen Access
Neural Target Speech Extraction: An overview
IEEE Signal Processing Magazine·2023· 92 cited
Neural Target Speech Extraction: An Overview
arXiv (Cornell University)·2023· 3 citedOpen Access
Listen only to me! How well can target speech extraction handle false alarms?
Interspeech 2022·2022· 22 cited
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model
Interspeech 2022·2022· 1 cited
Analysis of Impact of Emotions on Target Speech Extraction and Speech Separation
2022· 3 cited
Source Separation for Sound Event Detection in Domestic Environments using Jointly Trained Models
2022· 1 citedOpen Access
Analysis of impact of emotions on target speech extraction and speech separation
arXiv (Cornell University)·2022· 1 citedOpen Access
Listen only to me! How well can target speech extraction handle false alarms?
arXiv (Cornell University)·2022· 3 citedOpen Access
Revisiting Joint Decoding Based Multi-Talker Speech Recognition withDNN Acoustic Model
HAL (Le Centre pour la Communication Scientifique Directe)·2021
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model
arXiv (Cornell University)·2021Open Access
BUT system for the first Clarity enhancement challenge
2021
Auxiliary Loss Function for Target Speech Extraction and Recognition with Weak Supervision Based on Speaker Characteristics
2021· 7 cited
Jointly Trained Transformers Models for Spoken Language Translation
2021· 5 citedOpen Access
Speaker Activity Driven Neural Speech Extraction
2021· 35 cited
page 1 of 2Next →

Frequent Co-authors

Marc Delcroix(26), Keisuke Kinoshita(17), Tsubasa Ochiai(16), Tomohiro Nakatani(16), Jaň Černocký(15), Lukáš Burget(13), Ladislav Mošner(6), Shoko Araki(5), Martin Karafiát(5), Atsunori Ogawa(4), Takuya Higuchi(4), Karel Veselý(4), Shinji Watanabe(4), Federico Landini(4), Ondřej Novotný(4), Oldřich Plchot(4), Martin Kocour(4), Ján Švec(4), Ruiming Xie(4), Yashesh Gaur(4)