Kris Demuynck

Publication Activity (10 Years)

Years Active: 1994-2023
Publications (10 Years): 46

Top Venues

CoRR

INTERSPEECH

ICASSP

Comput. Speech Lang.

Katholieke Universiteit Leuven, Belgium (PHD)

Education History

Katholieke Universiteit Leuven, Belgium

PHD

Publications

François Remy, Kris Demuynck, Thomas Demeester
BioLORD-2023: Semantic Textual Representations Fusing LLM and Clinical Knowledge Graph Insights. CoRR (2023)
Geoffroy Vanderreydt, Amrutha Prasad, Driss Khalil, Srikanth R. Madikeri, Kris Demuynck, Petr Motlícek
Parameter-Efficient Tuning with Adaptive Bottlenecks for Automatic Speech Recognition. ASRU (2023)
François Remy, Kris Demuynck, Thomas Demeester
Automatic Glossary of Clinical Terminology: a Large-Scale Dictionary of Biomedical Definitions Generated from Ontological Knowledge. BioNLP@ACL (2023)
François Remy, Pieter Delobelle, Bettina Berendt, Kris Demuynck, Thomas Demeester
Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation. CoRR (2023)
Jenthe Thienpondt, Nilesh Madhu, Kris Demuynck
Margin-Mixup: A Method for Robust Speaker Verification in Multi-Speaker Audio. CoRR (2023)
Jenthe Thienpondt, Nilesh Madhu, Kris Demuynck
Margin-Mixup: A Method for Robust Speaker Verification In Multi-Speaker Audio. ICASSP (2023)
Jenthe Thienpondt, Kris Demuynck
ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings. ASRU (2023)
Anup Singh, Kris Demuynck, Vipul Arora
Simultaneously Learning Robust Audio Embeddings and Balanced Hash Codes for Query-by-Example. ICASSP (2023)
Geoffroy Vanderreydt, François Remy, Kris Demuynck
Transfer Learning from Multi-Lingual Speech Translation Benefits Low-Resource Speech Recognition. INTERSPEECH (2022)
Anup Singh, Kris Demuynck, Vipul Arora
Attention-Based Audio Embeddings for Query-by-Example. CoRR (2022)
Jenthe Thienpondt, Kris Demuynck
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping. CoRR (2022)
François Remy, Kris Demuynck, Thomas Demeester
BioLORD: Learning Ontological Representations from Definitions for Biomedical Concepts and their Textual Descriptions. EMNLP (Findings) (2022)
Jenthe Thienpondt, Kris Demuynck
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping. INTERSPEECH (2022)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information. ICASSP (2022)
Anup Singh, Kris Demuynck, Vipul Arora
Simultaneously Learning Robust Audio Embeddings and balanced Hash codes for Query-by-Example. CoRR (2022)
François Remy, Kris Demuynck, Thomas Demeester
BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions). CoRR (2022)
Anup Singh, Kris Demuynck, Vipul Arora
Attention-based audio embeddings for query-by-example. ISMIR (2022)
Siyuan Song, Brecht Desplanques, Kris Demuynck, Nilesh Madhu
SoftVAD in iVector-Based Acoustic Scene Classification for Robustness to Foreground Speech. EUSIPCO (2022)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information. CoRR (2021)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
The IDLAB VoxCeleb Speaker Recognition Challenge 2021 System Description. CoRR (2021)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification. Interspeech (2021)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
The Idlab Voxsrc-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification. ICASSP (2021)
Siyuan Song, Brecht Desplanques, Celest De Moor, Kris Demuynck, Nilesh Madhu
Robust Acoustic Scene Classification in the Presence of Active Foreground Speech. EUSIPCO (2021)
Siyuan Song, Brecht Desplanques, Celest De Moor, Kris Demuynck, Nilesh Madhu
Robust Acoustic Scene Classification in the Presence of Active Foreground Speech. CoRR (2021)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification. CoRR (2020)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
The IDLAB VoxCeleb Speaker Recognition Challenge 2020 System Description. CoRR (2020)
Brecht Desplanques, Jenthe Thienpondt, Kris Demuynck
ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. INTERSPEECH (2020)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization. INTERSPEECH (2020)
Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck
Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization. CoRR (2020)
Brecht Desplanques, Jenthe Thienpondt, Kris Demuynck
ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification. CoRR (2020)
Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, Thomas Demeester
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules? CoRR (2018)
Azarakhsh Jalalvand, Kris Demuynck, Wesley De Neve, Jean-Pierre Martens
On the application of reservoir computing networks for noisy image recognition. Neurocomputing 277 (2018)
Brecht Desplanques, Kris Demuynck
Cross-lingual Speech Emotion Recognition through Factor Analysis. INTERSPEECH (2018)
Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, Thomas Demeester
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules? EMNLP (2018)
Rob van Son, Catherine Middag, Kris Demuynck
Vowel Space as a Tool to Evaluate Articulation Problems. INTERSPEECH (2018)
Brecht Desplanques, Kris Demuynck, Jean-Pierre Martens
Adaptive speaker diarization of broadcast news based on factor analysis. Comput. Speech Lang. 46 (2017)
Brecht Desplanques, Kris Demuynck, Jean-Pierre Martens
Soft VAD in Factor Analysis Based Speaker Segmentation of Broadcast News. Odyssey (2016)
Lyan Verwimp, Brecht Desplanques, Kris Demuynck, Joris Pelemans, Marieke Lycke, Patrick Wambacq
STON: Efficient Subtitling in Dutch Using State-of-the-Art Tools. INTERSPEECH (2016)
Joris Pelemans, Tom Vanallemeersch, Kris Demuynck, Lyan Verwimp, Hugo Van hamme, Patrick Wambacq
Language model adaptation for ASR of spoken translations using phrase-based translation models and named entity models. ICASSP (2016)
Joris Pelemans, Lyan Verwimp, Kris Demuynck, Hugo Van hamme, Patrick Wambacq
SCALE: A Scalable Language Engineering Toolkit. LREC (2016)
Kseniya Proença, Kris Demuynck, Dirk Van Compernolle
Designing Syllable Models for an HMM Based Speech Recognition System. SPECOM (2016)
Joris Pelemans, Kris Demuynck, Hugo Van hamme, Patrick Wambacq
Improving n-gram probability estimates by compound-head clustering. ICASSP (2015)
Brecht Desplanques, Kris Demuynck, Jean-Pierre Martens
Factor analysis for speaker segmentation and improved speaker diarization. INTERSPEECH (2015)
Azarakhsh Jalalvand, Fabian Triefenbach, Kris Demuynck, Jean-Pierre Martens
Robust continuous digit recognition using Reservoir Computing. Comput. Speech Lang. 30 (1) (2015)
Yangyang Shi, Martha A. Larson, Joris Pelemans, Catholijn M. Jonker, Patrick Wambacq, Pascal Wiggers, Kris Demuynck
Integrating meta-information into recurrent neural network language models. Speech Commun. 73 (2015)
Joris Pelemans, Tom Vanallemeersch, Kris Demuynck, Hugo Van hamme, Patrick Wambacq
Efficient language model adaptation for automatic speech recognition of spoken translations. INTERSPEECH (2015)
Brecht Desplanques, Kris Demuynck, Jean-Pierre Martens
Combining Joint Factor Analysis and iVectors for Robust Language Recognition. Odyssey (2014)
Brecht Desplanques, Kris Demuynck, Jean-Pierre Martens
Robust language recognition via adaptive language factor extraction. INTERSPEECH (2014)
Joris Pelemans, Kris Demuynck, Hugo Van hamme, Patrick Wambacq
Speech Recognition Web Services for Dutch. LREC (2014)
Bert Réveil, Kris Demuynck, Jean-Pierre Martens
An improved two-stage mixed language model approach for handling out-of-vocabulary words in large vocabulary continuous speech recognition. Comput. Speech Lang. 28 (1) (2014)
Joris Pelemans, Kris Demuynck, Hugo Van hamme, Patrick Wambacq
Coping with language data sparsity: Semantic head mapping of compound words. ICASSP (2014)
Fabian Triefenbach, Kris Demuynck, Jean-Pierre Martens
Large Vocabulary Continuous Speech Recognition With Reservoir-Based Acoustic Models. IEEE Signal Process. Lett. 21 (3) (2014)
Fabian Triefenbach, Azarakhsh Jalalvand, Kris Demuynck, Jean-Pierre Martens
Context-dependent modeling and speaker normalization applied to reservoir-based phone recognition. INTERSPEECH (2013)
Azarakhsh Jalalvand, Kris Demuynck, Jean-Pierre Martens
Noise robust continuous digit recognition with reservoir-based acoustic models. ISPACS (2013)
Jort F. Gemmeke, Tuomas Virtanen, Kris Demuynck
Exemplar-based joint channel and noise compensation. ICASSP (2013)
Fabian Triefenbach, Azarakhsh Jalalvand, Kris Demuynck, Jean-Pierre Martens
Acoustic Modeling With Hierarchical Reservoirs. IEEE Trans. Speech Audio Process. 21 (11) (2013)
Azarakhsh Jalalvand, Kris Demuynck, Jean-Pierre Martens
Feature enhancement with a Reservoir-based Denoising Auto Encoder. ISSPIT (2013)
Kris Demuynck, Fabian Triefenbach
Porting concepts from DNNs back to GMMs. ASRU (2013)
Xueru Zhang, Kris Demuynck, Hugo Van hamme
Rapid speaker adaptation in latent speaker space with non-negative matrix factorization. Speech Commun. 55 (9) (2013)
Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo, Dimitri Kanevsky, Dirk Van Compernolle, Kris Demuynck, Jort F. Gemmeke, Jerome R. Bellegarda, Shiva Sundaram
Exemplar-Based Processing for Speech Recognition: An Overview. IEEE Signal Process. Mag. 29 (6) (2012)
Xueru Zhang, Kris Demuynck, Hugo Van hamme
Latent variable speaker adaptation of Gaussian mixture weights and means. ICASSP (2012)
Joris Pelemans, Kris Demuynck, Patrick Wambacq
A layered approach for dutch large vocabulary continuous speech recognition. ICASSP (2012)
Joris Pelemans, Kris Demuynck, Patrick Wambacq
Dutch Automatic Speech Recognition on the Web: Towards a General Purpose System. INTERSPEECH (2012)
Fabian Triefenbach, Kris Demuynck, Jean-Pierre Martens
Improving large vocabulary continuous speech recognition by combining GMM-based and reservoir-based acoustic modeling. SLT (2012)
Xueru Zhang, Kris Demuynck, Dirk Van Compernolle, Hugo Van hamme
Subspace-GMM acoustic models for under-resourced languages: feasibility study. SLTU (2012)
Patrick Wambacq, Kris Demuynck
Efficiency of Speech Alignment for Semi-automated Subtitling in Dutch. TSD (2011)
Kris Demuynck, Dino Seppi, Dirk Van Compernolle, Patrick Nguyen, Geoffrey Zweig
Integrating meta-information into exemplar-based speech recognition with segmental conditional random fields. ICASSP (2011)
Xueru Zhang, Kris Demuynck, Hugo Van hamme
Rapid speaker adaptation with speaker adaptive training and non-negative matrix factorization. ICASSP (2011)
Kris Demuynck, Dino Seppi, Hugo Van hamme, Dirk Van Compernolle
Progress in example based automatic speech recognition. ICASSP (2011)
Dino Seppi, Kris Demuynck, Dirk Van Compernolle
Template-Based Automatic Speech Recognition Meets Prosody. INTERSPEECH (2011)
Geoffrey Zweig, Patrick Nguyen, Dirk Van Compernolle, Kris Demuynck, Les E. Atlas, Pascal Clark, Gregory Sell, Meihong Wang, Fei Sha, Hynek Hermansky, Damianos G. Karakos, Aren Jansen, Samuel Thomas, Sivaram G. S. V. S., Samuel R. Bowman, Justine T. Kao
Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop. ICASSP (2011)
Toomas Altosaar, Louis ten Bosch, Guillaume Aimetti, Christos Koniaris, Kris Demuynck, Henk van den Heuvel
A Speech Corpus for Modeling Language Acquisition: CAREGIVER. LREC (2010)
Kris Demuynck, Xueru Zhang, Dirk Van Compernolle, Hugo Van hamme
Feature versus model based noise robustness. INTERSPEECH (2010)
Xueru Zhang, Kris Demuynck, Hugo Van hamme
Histogram equalization and noise masking for robust speech recognition. ICASSP (2010)
Jacques Duchateau, Yuk On Kong, Leen Cleuren, Lukas Latacz, Jan Roelens, Abdurrahman Samir, Kris Demuynck, Pol Ghesquière, Werner Verhelst, Hugo Van hamme
Developing a reading tutor: Design and evaluation of dedicated speech recognition and synthesis modules. Speech Commun. 51 (10) (2009)
Kris Demuynck, Antti Puurula, Dirk Van Compernolle, Patrick Wambacq
The ESAT 2008 system for N-Best Dutch speech recognition benchmark. ASRU (2009)
Jacques Duchateau, Kris Demuynck, Hugo Van hamme
Evaluation of phone lattice based speech decoding. INTERSPEECH (2009)
Jacques Duchateau, Tobias Leroy, Kris Demuynck, Hugo Van hamme
Fast speaker adaptation using non-negative matrix factorization. ICASSP (2008)
Alexander Bertrand, Kris Demuynck, Veronique Stouten, Hugo Van hamme
Unsupervised learning of auditory filter banks using non-negative matrix factorisation. ICASSP (2008)
Veronique Stouten, Kris Demuynck, Hugo Van hamme
Discovering Phone Patterns in Spoken Utterances by Non-Negative Matrix Factorization. IEEE Signal Process. Lett. 15 (2008)
Kris Demuynck, Jan Roelens, Dirk Van Compernolle, Patrick Wambacq
SPRAAK: an open source "SPeech recognition and automatic annotation kit". INTERSPEECH (2008)
Veronique Stouten, Kris Demuynck, Hugo Van hamme
Automatically learning the units of speech by non-negative matrix factorisation. INTERSPEECH (2007)
Mathias De Wachter, Kris Demuynck, Patrick Wambacq, Dirk Van Compernolle
Evaluating acoustic distance measures for template based recognition. INTERSPEECH (2007)
Mathias De Wachter, Kris Demuynck, Dirk Van Compernolle
Outlier Correction for Local Distance Measures in Example Based Speech Recognition. ICASSP (4) (2007)
Mathias De Wachter, Mike Matton, Kris Demuynck, Patrick Wambacq, Ronald Cools, Dirk Van Compernolle
Template-Based Continuous Speech Recognition. IEEE Trans. Speech Audio Process. 15 (4) (2007)
Quan Vu, Kris Demuynck, Dirk Van Compernolle
Vietnamese Automatic Speech Recognition: The FLaVoR Approach. ISCSLP (2006)
Kris Demuynck, Dirk Van Compernolle, Hugo Van hamme
Robust phone lattice decoding. INTERSPEECH (2006)
Mathias De Wachter, Kris Demuynck, Dirk Van Compernolle
Boosting HMM performance with a memory upgrade. INTERSPEECH (2006)
Mathias De Wachter, Kris Demuynck, Patrick Wambacq, Dirk Van Compernolle
A locally weighted distance measure for example based speech recognition. ICASSP (1) (2004)
Kris Demuynck, Tom Laureys, Patrick Wambacq, Dirk Van Compernolle
Automatic Phonemic Labeling and Segmentation of Spoken Dutch. LREC (2004)
Kris Demuynck, Oscar Garcia, Dirk Van Compernolle
Synthesizing speech from speech recognition parameters. INTERSPEECH (2004)
Veronique Stouten, Hugo Van hamme, Kris Demuynck, Patrick Wambacq
Robust speech recognition using model-based feature enhancement. INTERSPEECH (2003)
Mathias De Wachter, Kris Demuynck, Dirk Van Compernolle, Patrick Wambacq
Data driven example based continuous speech recognition. INTERSPEECH (2003)
Kris Demuynck, Tom Laureys, Dirk Van Compernolle, Hugo Van hamme
FLavor: a flexible architecture for LVCSR. INTERSPEECH (2003)
Kris Demuynck, Dirk Van Compernolle, Patrick Wambacq
Doing away with the Viterbi approximation. ICASSP (2002)
Kris Demuynck, Tom Laureys
A Comparison of Different Approaches to Automatic Speech Segmentation. TSD (2002)
Annemie Van Hirtum, Daniel Berckmans, Kris Demuynck, Dirk Van Compernolle
Autoregressive acoustical modelling of free field cough sound. ICASSP (2002)
Jacques Duchateau, Tom Laureys, Kris Demuynck, Patrick Wambacq
Handling Disfluencies in Spontaneous Language Models. CLIN (2002)
Kris Demuynck, Tom Laureys, Steven Gillis
Automatic generation of phonetic transcriptions for large speech corpora. INTERSPEECH (2002)
Jacques Duchateau, Kris Demuynck, Patrick Wambacq
Confidence scoring based on backward language models. ICASSP (2002)

Kris Demuynck.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Kris Demuynck