Research Explorer

Your browser does not support JavaScript or JavaScript is not enabled. Without JavaScript some functions of this webapplication may be disabled or cause error messages. To enable JavaScript, please consult the manual of your browser or contact your system administrator.

Researcher

Kris Demuynck

Publications & Research Data

Awards & Distinctions

80 Results

2026

More with Less: Strategies for Building Robust and Efficient Speech Recognition Models

Geoffroy VanderreydtKris DemuynckVeronique Hoste

2025

BEST-STD : bidirectional mamba-enhanced speech tokenization for spoken term detection

Anup SinghKris DemuynckVipul Arora

Factors influencing objective voice profile and speech intelligibility of patients after oral oncological treatment : a prospective cohort study

Jenthe ThienpondtKris DemuynckMatthias A. W. MerkxCaroline M. Speksnijder

A1 Journal Article in SUPPORTIVE CARE IN CANCER

Language-agnostic speech tokenizer for spoken term detection with efficient retrieval

Anup SinghKris DemuynckVipul Arora

Memory-efficient model growth for finetuning automatic speech recognition models

Geoffroy VanderreydtJenthe ThienpondtKris Demuynck

Single-channel speech enhancement with prior knowledge

Yanjue SongNilesh MadhuKris Demuynck

Towards audio context-aware hearing augmentation

Siyuan SongNilesh MadhuKris Demuynck

Weakly supervised phonological features for pathological speech analysis

Jenthe ThienpondtGeoffroy VanderreydtAbdessalem HammamiKris Demuynck

2024

A novel channel estimate for noise robust speech recognition

Geoffroy VanderreydtKris Demuynck

A1 Journal Article in COMPUTER SPEECH AND LANGUAGE

BioLORD-2023 : semantic textual representations fusing large language models and clinical knowledge graph insights

François RemyKris DemuynckThomas Demeester

A1 Journal Article in JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION

Deciphering the semantics of biomedical texts

François RemyKris DemuynckThomas Demeester

Ecologically valid speech collection in behavioral research : the Ghent Semi-spontaneous Speech Paradigm (GSSP)

Jonas Van Der DoncktMitchel KappenVicky DegraeveKris DemuynckMarie-Anne VanderhasseltSofie Van Hoecke

A1 Journal Article in BEHAVIOR RESEARCH METHODS

FlowHash : accelerating audio search with balanced hashing via normalizing flow

Anup SinghKris DemuynckVipul Arora

A1 Journal Article in IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING

Spatially selective speaker separation : bridging the gap between blind and strongly location guided methods

Alexander BohlenderNilesh MadhuKris Demuynck

Speaker embeddings with weakly supervised voice activity detection for efficient speaker diarization

Jenthe ThienpondtKris Demuynck

2023

Automatic glossary of clinical terminology : a large-scale dictionary of biomedical definitions generated from ontological knowledge

François RemyKris DemuynckThomas Demeester

Behavioral analysis of pathological speaker embeddings of patients during oncological treatment of oral cancer

Jenthe ThienpondtCaroline M. SpeksnijderKris Demuynck

ECAPA2 : a hybrid neural network architecture and training strategy for robust speaker embeddings

Jenthe ThienpondtKris Demuynck

Margin-mixup : a method for robust speaker verification in multi-speaker audio

Jenthe ThienpondtNilesh MadhuKris Demuynck

Parameter-efficient tuning with adaptive bottlenecks for automatic speech recognition

Geoffroy VanderreydtAmrutha PrasadDriss KhalilSrikanth MadikeriKris DemuynckPetr Motlicek

Simultaneously learning robust audio embeddings and balanced hash codes for query-by-example

Anup SinghKris DemuynckVipul Arora

2022

Attention-based audio embeddings for query-by-example

Anup SinghKris DemuynckVipul Arora

BioLORD : learning ontological representations from definitions for biomedical concepts and their textual descriptions

François RemyKris DemuynckThomas Demeester

SoftVAD in iVector-based acoustic scene classification for robustness to foreground speech

Siyuan SongBrecht DesplanquesKris DemuynckNilesh Madhu

Speech as an indicator for psychosocial stress : a network analytic approach

Mitchel KappenKristof HoorelbekeNilesh MadhuKris DemuynckMarie-Anne Vanderhasselt

A1 Journal Article in BEHAVIOR RESEARCH METHODS

Tackling the score shift in cross-lingual speaker verification by exploiting language information

Jenthe ThienpondtBrecht DesplanquesKris Demuynck

Taming large lexicons : translating clinical text using medical ontologies and sentence templates

François RemyP. De JaegerKris Demuynck

Transfer learning for robust low-resource children’s speech ASR with transformers and source-filter warping

Jenthe ThienpondtKris Demuynck

Transfer learning from multi-lingual speech translation benefits low-resource speech recognition

Geoffroy VanderreydtFrançois RemyKris Demuynck

2021

Integrating frequency translational invariance in TDNNs and frequency positional information in 2D ResNets to enhance speaker verification

Jenthe ThienpondtBrecht DesplanquesKris Demuynck

Is high-intensity speech intervention better? A comparison of high-intensity intervention versus low-intensity intervention in children with a cleft palate

Cassandra AlighieriKristiane Van LierdeAnne-Sophie De CaesemaekerKris DemuynckLaura BruneelEvelien D'haeseleerKim Bettens

A1 Journal Article in JOURNAL OF SPEECH LANGUAGE AND HEARING RESEARCH

Parents’ perceptions on speech therapy delivery models in children with a cleft palate : a mixed methods study

Cassandra AlighieriKim BettensLaure VanoostKris DemuynckSofie VerhaegheKristiane Van Lierde

A1 Journal Article in INTERNATIONAL JOURNAL OF PEDIATRIC OTORHINOLARYNGOLOGY

Robust acoustic scene classification in the presence of active foreground speech

Siyuan SongBrecht DesplanquesCelest De MoorKris DemuynckNilesh Madhu

The Idlab voxsrc-20 submission : large margin fine-tuning and quality-aware score calibration in DNN based speaker verification

Jenthe ThienpondtBrecht DesplanquesKris Demuynck

2020

Cross-lingual speaker verification with domain-balanced hard prototype mining and language-dependent score normalization

Jenthe ThienpondtBrecht DesplanquesKris Demuynck

ECAPA-TDNN : Emphasized Channel Attention, Propagation and Aggregation in TDNN based speaker verification

Brecht DesplanquesJenthe ThienpondtKris Demuynck

2019

Comprehensive integration of linguistic features in a human inspired speech recognition architecture

Claudia Matos VelizKris DemuynckVeronique Hoste

2018

Cross-lingual speech emotion recognition through factor analysis

Brecht DesplanquesKris Demuynck

Explaining character-aware neural networks for word-level prediction : do they discover linguistic rules?

Fréderic GodinKris DemuynckJoni DambreWesley De NeveThomas Demeester

On the application of reservoir computing networks for noisy image recognition

Azarakhsh JalalvandKris DemuynckWesley De NeveJean-Pierre Martens

A1 Journal Article in NEUROCOMPUTING

Vowel space as a tool to evaluate articulation problems

Rob J. J. H. van SonCatherine MiddagKris Demuynck

2017

Adaptive speaker diarization of broadcast news based on factor analysis

Brecht DesplanquesKris DemuynckJean-Pierre Martens

A1 Journal Article in COMPUTER SPEECH AND LANGUAGE

TTNWW to the rescue : no need to know how to handle tools and resources

Marc Kemps-SnijdersIneke SchuurmanWalter DaelemansKris DemuynckBrecht DesplanquesVeronique HosteMarijn HuijbregtsJean-Pierre MartensJoris PelemansMartin Reynaert et al.

Bookchapter in CLARIN in the Low Countries

2016

Language model adaptation for ASR of spoken translations using phrase-based translation models and named entity models

Joris PelemansTom VanallemeerschLyan VerwimpKris DemuynckHugo Van hammePatrick Wambacq

Soft VAD in factor analysis based speaker segmentation of broadcast news

Brecht DesplanquesKris DemuynckJean-Pierre Martens

STON efficient subtitling in Dutch using state-of-the-art tools

Lyan VerwimpBrecht DesplanquesKris DemuynckJoris PelemansMariek LyckePatrick Wambacq

2015

Design of reservoir computing systems for noise-robust speech and handwriting recognition

Azarakhsh JalalvandKris DemuynckWesley De NeveRik Van de WalleJean-Pierre Martens

Design of reservoir computing systems for the recognition of noise corrupted speech and handwriting

Azarakhsh JalalvandJean-Pierre MartensKris Demuynck

Efficient language model adaptation for automatic speech recognition of spoken translations

Joris PelemansTom VanallemeerschKris DemuynckHugo Van hammePatrick Wambacq

Factor analysis for speaker segmentation and improved speaker diarization

Brecht DesplanquesKris DemuynckJean-Pierre Martens

Improving N-gram probabilities by compound-head clustering

Joris PelemansKris DemuynckHugo Van hammePatrick Wambacq

Improving N-Gram probability estimates by compound-head clustering

Joris PelemansKris DemuynckHugo Van HammePatrick Wambacq

Integrating meta-information into recurrent neural network language models

Yangyang ShiMartha LarsonJoris PelemansCatholijn M JonckerPatrick WambacqPascal WiggersKris Demuynck

A1 Journal Article in SPEECH COMMUNICATION

Robust continuous digit recognition using reservoir computing

Azarakhsh JalalvandFabian TriefenbachKris DemuynckJean-Pierre Martens

A1 Journal Article in COMPUTER SPEECH AND LANGUAGE

2014

An improved two-stage mixed language model approach for handling out-of-vocabulary words in large vocabulary continuous speech recognition

Bert RéveilKris DemuynckJean-Pierre Martens

A1 Journal Article in COMPUTER SPEECH AND LANGUAGE

Combining joint factor analysis and iVectors for robust language recognition

Brecht DesplanquesKris DemuynckJean-Pierre Martens

Coping with language data sparsity: semantic head mapping for compound words

Joris PelemansKris DemuynckHugo Van hammePatrick Wambacq

Large vocabulary continuous speech recognition with reservoir-based acoustic models

Fabian TriefenbachKris DemuynckJean-Pierre Martens

A1 Journal Article in IEEE SIGNAL PROCESSING LETTERS

Robust language recognition via adaptive language factor extraction

Brecht DesplanquesKris DemuynckJean-Pierre Martens

Speech recognition web services for Dutch

Joris PelemansKris DemuynckHugo Van hammePatrick Wambacq

The effect of word similarity on N-gram language models in Northern and Southern Dutch

Joris PelemansKris DemuynckHugo Van DammePatrick Wambacq

A2 Journal Article in COMPUTATIONAL LINGUISTICS IN THE NETHERLANDS JOURNAL

2013

Acoustic modeling with hierarchical reservoirs

Fabian TriefenbachAzarakhsh JalalvandKris DemuynckJean-Pierre Martens

A1 Journal Article in IEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

Automatic syllabification using segmental conditional random fields

Kseniya RogovaKris DemuynckDirk Van Compernolle

A2 Journal Article in COMPUTATIONAL LINGUISTICS IN THE NETHERLANDS JOURNAL

Context-dependent modeling and speaker normalization applied to reservoir-based phone recognition

Fabian TriefenbachAzarakhsh JalalvandKris DemuynckJean-Pierre Martens

Exemplar-based joint channel and noise compensation

Jort F GemmekeTuomas VirtanenKris Demuynck

Feature enhancement with a reservoir-based denoising auto encoder

Azarakhsh JalalvandKris DemuynckJean-Pierre Martens

Missing data solutions for robust speech recognition

Yujun WangGemmeke JortKris DemuynckHugo Van hamme

Bookchapter in Essential speech and language technology for Dutch

Noise robust continuous digit recognition with reservoir-based acoustic models

Azarakhsh JalalvandKris DemuynckJean-Pierre Martens

Porting concepts from DNNs back to GMMs

Kris DemuynckFabian Triefenbach

Rapid speaker adaptation in latent speaker space with non-negative matrix factorization

Xueru ZhangKris DemuynckHugo Van hamme

A1 Journal Article in SPEECH COMMUNICATION

SPRAAK: speech processing, recognition and automatic annotation kit

Patrick WambacqKris DemuynckDirk Van Compernolle

Bookchapter in Essential speech and language technology for Dutch

2012

A layered approach for Dutch large vocabulary continuous speech recognition

Joris PelemansKris DemuynckPatrick Wambacq

Dutch automatic speech recognition on the web: towards a general purpose system

Joris PelemansKris DemuynckPatrick Wambacq

Exemplar-based processing for speech recognition

Tara N SinathBhuvana RamabhadranDavid NahamooDimitri KanevskyDirk Van CompernolleKris DemuynckJort F GemmekeJerome R BellegardaShiva Sundaram

A1 Journal Article in IEEE SIGNAL PROCESSING MAGAZINE

Improving large vocabulary continuous speech recognition by combining GMM-based and reservoir-based acoustic modeling

Fabian TriefenbachKris DemuynckJean-Pierre Martens

Latent variable speaker adaptation of gaussian mixture weights and means

Xueru ZhangKris DemuynckHugo Van hamme

Subspace-GMM acoustic models for under-resourced languages: feasibility study

Xueru ZhangKris DemuynckDirk Van CompernolleHugo Van hamme

2009

Developing a reading tutor : design and evaluation of dedicated speech recognition and synthesis modules

Jacques DuchateauYuk On KongLeen CleurenLukas LataczJan RoelensAbdurrahman SamirKris DemuynckPol GhesquiereWerner VerhelstHugo Van Hamme

A1 Journal Article in SPEECH COMMUNICATION

2007

Template-based continuous speech recognition

Mathias De WachterMike MattonKris DemuynckPatrick WambacqRonald CoolsDirk Van Compernolle

A1 Journal Article in IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING

2000

An efficient search space representation for large vocabulary continuous speech recognition

Kris DemuynckJacques DuchateauDirk Van CompernollePatrick Wambacq

A1 Journal Article in SPEECH COMMUNICATION