Milos Cernak - RankMe

110 papers A 29B 1C 1Misc 14Journal 45Unranked 19

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Calibration-Reasoning Framework for Descriptive Speech Quality Assessment. CoRR Elizaveta Kostenok, Mathieu Salzmann, Milos Cernak
2026	J	`jnl`	Differentiable Time-Varying IIR Filtering for Real-Time Speech Denoising. CoRR Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff, Milos Cernak
2025	A	`conf`	DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration. INTERSPEECH Sanberk Serbest, Tijana Stojkovic, Milos Cernak, Andrew Harper
2025	J	`jnl`	DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration. CoRR Sanberk Serbest, Tijana Stojkovic, Milos Cernak, Andrew Harper
2025	A	`conf`	Model as Loss: A Self-Consistent Training Paradigm. INTERSPEECH Saisamarth Rajesh Phaye, Milos Cernak, Andrew Harper
2025	J	`jnl`	Model as Loss: A Self-Consistent Training Paradigm. CoRR Saisamarth Rajesh Phaye, Milos Cernak, Andrew Harper
2025	Misc	`conf`	OpenACE: An Open Benchmark for Evaluating Audio Coding Performance. ICASSP Jozef Coldenhoff, Niclas Granqvist, Milos Cernak
2025	Misc	`conf`	Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task. ICASSP Jozef Coldenhoff, Milos Cernak
2025	J	`jnl`	Shortcut Flow Matching for Speech Enhancement: Step-Invariant flows via single stage training. CoRR Naisong Zhou, Saisamarth Rajesh Phaye, Milos Cernak, Tijana Stojkovic, Andy Pearce, Andrea Cavallaro, Andy Harper
2024	J	`jnl`	Diffusion-based Speech Enhancement with Schrödinger Bridge and Symmetric Noise Schedule. CoRR Siyi Wang, Siyi Liu, Andrew Harper, Paul Kendrick, Mathieu Salzmann, Milos Cernak
2024	Misc	`conf`	Multi-Channel Mosra: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and A Teacher Model. ICASSP Jozef Coldenhoff, Andrew Harper, Paul Kendrick, Tijana Stojkovic, Milos Cernak
2024	Misc	`conf`	On Real-Time Multi-Stage Speech Enhancement Systems. ICASSP Lingjun Meng, Jozef Coldenhoff, Paul Kendrick, Tijana Stojkovic, Andrew Harper, Kiril Ratmanski, Milos Cernak
2024	J	`jnl`	OpenACE: An Open Benchmark for Evaluating Audio Coding Performance. CoRR Jozef Coldenhoff, Niclas Granqvist, Milos Cernak
2024	J	`jnl`	Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task. CoRR Jozef Coldenhoff, Milos Cernak
2023	A	`conf`	ALO-VC: Any-to-any Low-latency One-shot Voice Conversion. INTERSPEECH Bohan Wang, Damien Ronssin, Milos Cernak
2023	J	`jnl`	ALO-VC: Any-to-any Low-latency One-shot Voice Conversion. CoRR Bohan Wang, Damien Ronssin, Milos Cernak
2023	J	`jnl`	Cluster-based pruning techniques for audio data. CoRR Boris Bergsma, Marta Brzezinska, Oleg V. Yazyev, Milos Cernak
2023	—	`conf`	Demo Abstract: In-Ear-Voice - Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms. IoTDI Philipp Schilk, Niccolò Polvani, Andrea Ronco, Milos Cernak, Michele Magno
2023	Misc	`conf`	Efficient Speech Quality Assessment Using Self-Supervised Framewise Embeddings. ICASSP Karl El Hajal, Zihan Wu, Neil Scheidwasser-Clow, Gasser Elbanna, Milos Cernak
2023	—	`conf`	In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms. IoTDI Philipp Schilk, Niccolò Polvani, Andrea Ronco, Milos Cernak, Michele Magno
2023	J	`jnl`	In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms. CoRR Philipp Schilk, Niccolò Polvani, Andrea Ronco, Milos Cernak, Michele Magno
2023	J	`jnl`	Multi-Channel MOSRA: Mean Opinion Score and Room Acoustics Estimation Using Simulated Data and a Teacher Model. CoRR Jozef Coldenhoff, Andrew Harper, Paul Kendrick, Tijana Stojkovic, Milos Cernak
2023	Misc	`conf`	Personalized Task Load Prediction in Speech Communication. ICASSP Robert P. Spang, Karl El Hajal, Sebastian Möller, Milos Cernak
2023	J	`jnl`	Personalized Task Load Prediction in Speech Communication. CoRR Robert P. Spang, Karl El Hajal, Sebastian Möller, Milos Cernak
2023	A	`conf`	Speaker Embeddings as Individuality Proxy for Voice Stress Detection. INTERSPEECH Zihan Wu, Neil Scheidwasser-Clow, Karl El Hajal, Milos Cernak
2023	J	`jnl`	Speaker Embeddings as Individuality Proxy for Voice Stress Detection. CoRR Zihan Wu, Neil Scheidwasser-Clow, Karl El Hajal, Milos Cernak
2022	A	`conf`	Application for Real-time Personalized Speaker Extraction. INTERSPEECH Damien Ronssin, Milos Cernak
2022	J	`jnl`	BC-VAD: A Robust Bone Conduction Voice Activity Detection. CoRR Niccolò Polvani, Damien Ronssin, Milos Cernak
2022	J	`jnl`	BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping. CoRR Gasser Elbanna, Neil Scheidwasser-Clow, Mikolaj Kegler, Pierre Beckmann, Karl El Hajal, Milos Cernak
2022	J	`jnl`	Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings. CoRR Karl El Hajal, Zihan Wu, Neil Scheidwasser-Clow, Gasser Elbanna, Milos Cernak
2022	—	`conf`	Fast accuracy estimation of deep learning based multi-class musical source separation. NLDL Alexandru Mocanu, Benjamin Ricaud, Milos Cernak
2022	A	`conf`	Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load. INTERSPEECH Gasser Elbanna, Alice Biryukov, Neil Scheidwasser-Clow, Lara Orlandic, Pablo Mainar, Mikolaj Kegler, Pierre Beckmann, Milos Cernak
2022	J	`jnl`	Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load. CoRR Gasser Elbanna, Alice Biryukov, Neil Scheidwasser-Clow, Lara Orlandic, Pablo Mainar, Mikolaj Kegler, Pierre Beckmann, Milos Cernak
2022	A	`conf`	MOSRA: Joint Mean Opinion Score and Room Acoustics Speech Quality Assessment. INTERSPEECH Karl El Hajal, Milos Cernak, Pablo Mainar
2022	J	`jnl`	MOSRA: Joint Mean Opinion Score and Room Acoustics Speech Quality Assessment. CoRR Karl El Hajal, Milos Cernak, Pablo Mainar
2022	A	`conf`	PEAF: Learnable Power Efficient Analog Acoustic Features for Audio Recognition. INTERSPEECH Boris Bergsma, Minhao Yang, Milos Cernak
2022	Misc	`conf`	SERAB: A Multi-Lingual Benchmark for Speech Emotion Recognition. ICASSP Neil Scheidwasser-Clow, Mikolaj Kegler, Pierre Beckmann, Milos Cernak
2021	—	`conf`	A Universal Deep Room Acoustics Estimator. WASPAA Paula Sánchez López, Paul Callens, Milos Cernak
2021	J	`jnl`	A Universal Deep Room Acoustics Estimator. CoRR Paula Sánchez López, Paul Callens, Milos Cernak
2021	C	`conf`	AC-VC: Non-Parallel Low Latency Phonetic Posteriorgrams Based Voice Conversion. ASRU Damien Ronssin, Milos Cernak
2021	J	`jnl`	AC-VC: Non-parallel Low Latency Phonetic Posteriorgrams Based Voice Conversion. CoRR Damien Ronssin, Milos Cernak
2021	—	`conf`	BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping. HEAR@NeurIPS Gasser Elbanna, Neil Scheidwasser-Clow, Mikolaj Kegler, Pierre Beckmann, Karl El Hajal, Milos Cernak
2021	A	`conf`	Non-Intrusive Speech Quality Assessment with Transfer Learning and Subject-Specific Scaling. Interspeech Natalia Nessler, Milos Cernak, Paolo Prandoni, Pablo Mainar
2021	J	`jnl`	Power efficient analog features for audio recognition. CoRR Boris Bergsma, Minhao Yang, Milos Cernak
2021	J	`jnl`	SERAB: A multi-lingual benchmark for speech emotion recognition. CoRR Neil Scheidwasser-Clow, Mikolaj Kegler, Pierre Beckmann, Milos Cernak
2021	—	`conf`	Word-Level Embeddings for Cross-Task Transfer Learning in Speech Processing. EUSIPCO Pierre Beckmann, Mikolaj Kegler, Milos Cernak
2020	Misc	`conf`	A Bin Encoding Training of a Spiking Neural Network Based Voice Activity Detection. ICASSP Giorgia Dellaferrera, Flavio Martinelli, Milos Cernak
2020	A	`conf`	Deep Speech Inpainting of Time-Frequency Masks. INTERSPEECH Mikolaj Kegler, Pierre Beckmann, Milos Cernak
2020	J	`jnl`	Fast accuracy estimation of deep learning based multi-class musical source separation. CoRR Alexandru Mocanu, Benjamin Ricaud, Milos Cernak
2020	—	`conf`	FastVC: Fast Voice Conversion with non-parallel data. Blizzard Challenge / Voice Conversion Challenge Oriol Barbany Mayor, Milos Cernak
2020	J	`jnl`	FastVC: Fast Voice Conversion with non-parallel data. CoRR Oriol Barbany Mayor, Milos Cernak
2020	J	`jnl`	Joint Blind Room Acoustic Characterization From Speech And Music Signals Using Convolutional Recurrent Neural Networks. CoRR Paul Callens, Milos Cernak
2020	Misc	`conf`	Spiking Neural Networks Trained With Backpropagation for Low Power Neuromorphic Implementation of Voice Activity Detection. ICASSP Flavio Martinelli, Giorgia Dellaferrera, Pablo Mainar, Milos Cernak
2019	J	`jnl`	A Bin Encoding Training of a Spiking Neural Network-based Voice Activity Detection. CoRR Giorgia Dellaferrera, Flavio Martinelli, Milos Cernak
2019	J	`jnl`	Deep speech inpainting of time-frequency masks. CoRR Mikolaj Kegler, Pierre Beckmann, Milos Cernak
2019	A	`conf`	End-to-End Accented Speech Recognition. INTERSPEECH Thibault Viglino, Petr Motlícek, Milos Cernak
2019	A	`conf`	Evaluating Audiovisual Source Separation in the Context of Video Conferencing. INTERSPEECH Berkay Inan, Milos Cernak, Helmut Grabner, Helena Peic Tukuljac, Rodrigo C. G. Pena, Benjamin Ricaud
2019	A	`conf`	Open-Vocabulary Keyword Spotting with Audio and Text Embeddings. INTERSPEECH Niccolò Sacchi, Alexandre Nanchen, Martin Jaggi, Milos Cernak
2019	A	`conf`	Phone-Attribute Posteriors to Evaluate the Speech of Cochlear Implant Users. INTERSPEECH Tomás Arias-Vergara, Juan Rafael Orozco-Arroyave, Milos Cernak, Sandra Gollwitzer, Maria Schuster, Elmar Nöth
2019	J	`jnl`	Speech-VGG: A deep feature extractor for speech processing. CoRR Pierre Beckmann, Mikolaj Kegler, Hugues Saltini, Milos Cernak
2019	J	`jnl`	Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection. CoRR Flavio Martinelli, Giorgia Dellaferrera, Pablo Mainar, Milos Cernak
2019	—	`ch.`	Voice Presentation Attack Detection Using Convolutional Neural Networks. Handbook of Biometric Anti-Spoofing, 2nd Ed. Ivan Himawan, Srikanth R. Madikeri, Petr Motlícek, Milos Cernak, Sridha Sridharan, Clinton Fookes
2018	J	`jnl`	Cognitive Speech Coding: Examining the Impact of Cognitive Speech Processing on Speech Compression. IEEE Signal Process. Mag. Milos Cernak, Afsaneh Asaei, Alexandre Hyafil
2018	Misc	`conf`	Nasal Speech Sounds Detection Using Connectionist Temporal Classification. ICASSP Milos Cernak, Sibo Tong
2018	J	`jnl`	NeuroSpeech. SoftwareX Juan Rafael Orozco-Arroyave, Juan Camilo Vásquez-Correa, Jesús Francisco Vargas-Bonilla, Raman Arora, Najim Dehak, Phani S. Nidadavolu, Heidi Christensen, Frank Rudzicz, Maria Yancheva, Hamid R. Chinaei, Alyssa Vann, Nikolai Vogler, Tobias Bocklet, Milos Cernak, Julius Hannink, Elmar Nöth
2018	J	`jnl`	NeuroSpeech: An open-source software for Parkinson's speech analysis. Digit. Signal Process. Juan Rafael Orozco-Arroyave, Juan Camilo Vásquez-Correa, Jesús Francisco Vargas-Bonilla, Raman Arora, Najim Dehak, Phani S. Nidadavolu, Heidi Christensen, Frank Rudzicz, Maria Yancheva, Hamid R. Chinaei, Alyssa Vann, Nikolai Vogler, Tobias Bocklet, Milos Cernak, Julius Hannink, Elmar Nöth
2018	—	`conf`	Phonological Posteriors and GRU Recurrent Units to Assess Speech Impairments of Patients with Parkinson's Disease. TSD Juan Camilo Vásquez-Correa, Nicanor García-Ospina, Juan Rafael Orozco-Arroyave, Milos Cernak, Elmar Nöth
2018	—	`conf`	Phonological i-Vectors to Detect Parkinson's Disease. TSD Nicanor García-Ospina, Tomás Arias-Vergara, Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Milos Cernak, Elmar Nöth
2017	A	`conf`	Bob Speaks Kaldi. INTERSPEECH Milos Cernak, Alain Komaty, Amir Mohammadi, André Anjos, Sébastien Marcel
2017	J	`jnl`	Characterisation of voice quality of Parkinson's disease using differential phonological posterior features. Comput. Speech Lang. Milos Cernak, Juan Rafael Orozco-Arroyave, Frank Rudzicz, Heidi Christensen, Juan Camilo Vásquez-Correa, Elmar Nöth
2017	Misc	`conf`	Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease. ICASSP Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Raman Arora, Elmar Nöth, Najim Dehak, Heidi Christensen, Frank Rudzicz, Tobias Bocklet, Milos Cernak, Hamid R. Chinaei, Julius Hannink, Phani Sankar Nidadavolu, Maria Yancheva, Alyssa Vann, Nikolai Vogler
2017	Misc	`conf`	On the impact of non-modal phonation on phonological features. ICASSP Milos Cernak, Elmar Nöth, Frank Rudzicz, Heidi Christensen, Juan Rafael Orozco-Arroyave, Raman Arora, Tobias Bocklet, Hamidreza Chinaei, Julius Hannink, Phani Sankar Nidadavolu, Juan Camilo Vásquez-Correa, Maria Yancheva, Alyssa Vann, Nikolai Vogler
2017	J	`jnl`	Perceptual Information Loss due to Impaired Speech Production. IEEE ACM Trans. Audio Speech Lang. Process. Afsaneh Asaei, Milos Cernak, Hervé Bourlard
2017	J	`jnl`	Speech vocoding for laboratory phonology. Comput. Speech Lang. Milos Cernak, Stefan Benus, Alexandros Lazaridis
2016	J	`jnl`	An Analysis of Rhythmic Staccato-Vocalization Based on Frequency Demodulation for Laughter Detection in Conversational Meetings. CoRR Sucheta Ghosh, Milos Cernak, Sarbani Palit, B. B. Chaudhuri
2016	J	`jnl`	Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding. CoRR Milos Cernak, Alexandros Lazaridis, Afsaneh Asaei, Philip N. Garner
2016	J	`jnl`	Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding. IEEE ACM Trans. Audio Speech Lang. Process. Milos Cernak, Alexandros Lazaridis, Afsaneh Asaei, Philip N. Garner
2016	A	`conf`	HMM-Based Non-Native Accent Assessment Using Posterior Features. INTERSPEECH Ramya Rasipuram, Milos Cernak, Mathew Magimai-Doss
2016	—	`conf`	Investigating Spectral Amplitude Modulation Phase Hierarchy Features in Speech Synthesis. SSW Alexandros Lazaridis, Milos Cernak, Pierre-Edouard Honnet, Philip N. Garner
2016	—	`conf`	Modeling unvoiced sounds in statistical parametric speech synthesis with a continuous vocoder. EUSIPCO Tamás Gábor Csapó, Géza Németh, Milos Cernak, Philip N. Garner
2016	J	`jnl`	On Structured Sparsity of Phonological Posteriors for Linguistic Parsing. CoRR Milos Cernak, Afsaneh Asaei, Hervé Bourlard
2016	J	`jnl`	On structured sparsity of phonological posteriors for linguistic parsing. Speech Commun. Milos Cernak, Afsaneh Asaei, Hervé Bourlard
2016	A	`conf`	PhonVoc: A Phonetic and Phonological Vocoding Toolkit. INTERSPEECH Milos Cernak, Philip N. Garner
2016	A	`conf`	Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures. INTERSPEECH Afsaneh Asaei, Gil Luyet, Milos Cernak, Hervé Bourlard
2016	A	`conf`	Probabilistic Amplitude Demodulation Features in Speech Synthesis for Improving Prosody. INTERSPEECH Alexandros Lazaridis, Milos Cernak, Philip N. Garner
2016	A	`conf`	Sound Pattern Matching for Automatic Prosodic Event Detection. INTERSPEECH Milos Cernak, Afsaneh Asaei, Pierre-Edouard Honnet, Philip N. Garner, Hervé Bourlard
2016	J	`jnl`	Speech vocoding for laboratory phonology. CoRR Milos Cernak, Stefan Benus, Alexandros Lazaridis
2015	A	`conf`	An empirical model of emphatic word detection. INTERSPEECH Milos Cernak, Pierre-Edouard Honnet
2015	A	`conf`	Automatic accentedness evaluation of non-native speech using phonetic and sub-phonetic posterior probabilities. INTERSPEECH Ramya Rasipuram, Milos Cernak, Alexandre Nanchen, Mathew Magimai-Doss
2015	J	`jnl`	Incremental Syllable-Context Phonetic Vocoding. IEEE ACM Trans. Audio Speech Lang. Process. Milos Cernak, Philip N. Garner, Alexandros Lazaridis, Petr Motlícek, Xingyu Na
2015	A	`conf`	Neuromorphic based oscillatory device for incremental syllable boundary detection. INTERSPEECH Alexandre Hyafil, Milos Cernak
2015	A	`conf`	On compressibility of neural network phonological features for low bit rate speech coding. INTERSPEECH Afsaneh Asaei, Milos Cernak, Hervé Bourlard
2015	Misc	`conf`	Phonological vocoding using artificial neural networks. ICASSP Milos Cernak, Blaise Potard, Philip N. Garner
2015	—	`conf`	Residual-Based Excitation with Continuous F0 Modeling in HMM-Based Speech Synthesis. SLSP Tamás Gábor Csapó, Géza Németh, Milos Cernak
2014	A	`conf`	Development of bilingual ASR system for MediaParl corpus. INTERSPEECH Petr Motlícek, David Imseng, Milos Cernak, Namhoon Kim
2014	A	`conf`	Stress and accent transmission in HMM-based syllable-context very low bit rate speech coding. INTERSPEECH Milos Cernak, Alexandros Lazaridis, Philip N. Garner, Petr Motlícek
2013	J	`jnl`	A Simple Continuous Pitch Estimation Algorithm. IEEE Signal Process. Lett. Philip N. Garner, Milos Cernak, Petr Motlícek
2013	B	`conf`	Automatic Staging of Audio with Emotions. ACII Lakshmi Babu Saheer, Milos Cernak
2013	Misc	`conf`	On the (UN)importance of the contextual factors in HMM-based speech synthesis and coding. ICASSP Milos Cernak, Petr Motlícek, Philip N. Garner
2013	A	`conf`	Syllable-based pitch encoding for low bit rate speech coding with recognition/synthesis architecture. INTERSPEECH Milos Cernak, Xingyu Na, Philip N. Garner
2012	—	`conf`	Reading companion: the technical and social design of an automated reading tutor. WOCCI Arthur Kantor, Milos Cernak, Jirí Havelka, Sean Huber, Jan Kleindienst, Doris B. Gonzalez
2012	A	`conf`	Robust triphone mapping for acoustic modeling. INTERSPEECH Milos Cernak, David Imseng, Hervé Bourlard
2011	A	`conf`	Effective Triphone Mapping for Acoustic Modeling in Speech Recognition. INTERSPEECH Sakhia Darjaa, Milos Cernak, Marián Trnka, Milan Rusko, Róbert Sabo
2011	—	`conf`	Rule-Based Triphone Mapping for Acoustic Modeling in Automatic Speech Recognition. TSD Sakhia Darjaa, Milos Cernak, Stefan Benus, Milan Rusko, Róbert Sabo, Marián Trnka
2010	J	`jnl`	A Comparison of Decision Tree Classifiers for Automatic Diagnosis of Speech Recognition Errors. Comput. Informatics Milos Cernak
2010	—	`conf`	Diagnostics for Debugging Speech Recognition Systems. TSD Milos Cernak
2006	—	`conf`	Diagnostics of speech recognition using classification phoneme diagnostic trees. Computational Intelligence Milos Cernak, Christian Wellekens
2006	—	`conf`	Unit Selection Speech Synthesis in Noise. ICASSP (1) Milos Cernak
2005	—	`conf`	TTSBOX: a MATLAB toolbox for teaching text-to-speech synthesis. ICASSP (5) Thierry Dutoit, Milos Cernak
2004	—	`conf`	Slovak Speech Database for Experiments and Application Building in Unit-Selection Speech Synthesis. TSD Milan Rusko, Marián Trnka, Sachia Darzágín, Milos Cernak