Irina Illina - RankMe

119 papers A 28B 6C 6Misc 7Journal 33Unranked 38

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Cross-lingual Matryoshka Representation Learning across Speech and Text. CoRR Yaya Sy, Dioula Doucouré, Christophe Cerisara, Irina Illina
2025	J	`jnl`	BEST-RQ-Based Self-Supervised Learning for Whisper Domain Adaptation. CoRR Raphaël Bagat, Irina Illina, Emmanuel Vincent
2025	J	`jnl`	BaldWhisper: Faster Whisper with Head Shearing and Layer Merging. CoRR Yaya Sy, Christophe Cerisara, Irina Illina
2025	—	`conf`	Efficient One-shot Compression via Low-Rank Local Feature Distillation. NAACL (Long Papers) Yaya Sy, Christophe Cerisara, Irina Illina
2025	A	`conf`	Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition. INTERSPEECH Raphaël Bagat, Irina Illina, Emmanuel Vincent
2025	J	`jnl`	Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition. CoRR Raphaël Bagat, Irina Illina, Emmanuel Vincent
2025	J	`jnl`	Speech Language Models for Under-Represented Languages: Insights from Wolof. CoRR Yaya Sy, Dioula Doucouré, Christophe Cerisara, Irina Illina
2024	J	`jnl`	Lillama: Large Language Models Compression via Low-Rank Feature Distillation. CoRR Yaya Sy, Christophe Cerisara, Irina Illina
2024	J	`jnl`	Training RNN language models on uncertain ASR hypotheses in limited data scenarios. Comput. Speech Lang. Imran A. Sheikh, Emmanuel Vincent, Irina Illina
2023	J	`jnl`	SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays. CoRR Nicolas Furnon, Romain Serizel, Slim Essid, Irina Illina
2022	B	`conf`	Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection. COLING Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr
2022	J	`jnl`	Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection. CoRR Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr
2022	—	`conf`	Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection. ACL (Findings) Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr
2022	J	`jnl`	Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection. CoRR Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr
2022	—	`conf`	Exploration of Multi-corpus Learning for Hate Speech Classification in Low Resource Scenarios. TSD Ashwin Geet D'Sa, Irina Illina, Dominique Fohr, Awais Akbar
2022	—	`conf`	Identification des Expressions Polylexicales dans les Tweets (Identification of Multiword Expressions in Tweets). TALN-RECITAL Nicolas Zampieri, Carlos Ramisch, Irina Illina, Dominique Fohr
2022	B	`conf`	Identification of Multiword Expressions in Tweets for Hate Speech Detection. LREC Nicolas Zampieri, Carlos Ramisch, Irina Illina, Dominique Fohr
2022	B	`conf`	Placing M-Phasis on the Plurality of Hate: A Feature-Based Corpus of Hate Online. LREC Dana Ruiter, Liane Reiners, Ashwin Geet D'Sa, Thomas Kleinbauer, Dominique Fohr, Irina Illina, Dietrich Klakow, Christian Schemer, Angeliki Monnier
2022	J	`jnl`	Placing M-Phasis on the Plurality of Hate: A Feature-Based Corpus of Hate Online. CoRR Dana Ruiter, Liane Reiners, Ashwin Geet D'Sa, Thomas Kleinbauer, Dominique Fohr, Irina Illina, Dietrich Klakow, Christian Schemer, Angeliki Monnier
2022	—	`conf`	Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection. AACL/IJCNLP (1) Tulika Bose, Irina Illina, Dominique Fohr
2022	J	`jnl`	Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection. CoRR Tulika Bose, Irina Illina, Dominique Fohr
2022	B	`conf`	Transformer versus LSTM Language Models trained on Uncertain ASR Hypotheses in Limited Data Scenarios. LREC Imran A. Sheikh, Emmanuel Vincent, Irina Illina
2021	—	`conf`	Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes. EUSIPCO Nicolas Furnon, Romain Serizel, Slim Essid, Irina Illina
2021	J	`jnl`	Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes. CoRR Nicolas Furnon, Romain Serizel, Slim Essid, Irina Illina
2021	A	`conf`	BERT-Based Semantic Model for Rescoring N-Best Speech Recognition List. Interspeech Dominique Fohr, Irina Illina
2021	J	`jnl`	DNN-Based Mask Estimation for Distributed Speech Enhancement in Spatially Unconstrained Microphone Arrays. IEEE ACM Trans. Audio Speech Lang. Process. Nicolas Furnon, Romain Serizel, Slim Essid, Irina Illina
2021	—	`conf`	DNN-Based Semantic Rescoring Models for Speech Recognition. TDS Irina Illina, Dominique Fohr
2021	Misc	`conf`	Distributed Speech Separation in Spatially Unconstrained Microphone Arrays. ICASSP Nicolas Furnon, Romain Serizel, Irina Illina, Slim Essid
2021	—	`conf`	Exploring Conditional Language Model Based Data Augmentation Approaches for Hate Speech Classification. TDS Ashwin Geet D'Sa, Irina Illina, Dominique Fohr, Dietrich Klakow, Dana Ruiter
2021	J	`jnl`	Improving Automatic Hate Speech Detection with Multiword Expression Features. CoRR Nicolas Zampieri, Irina Illina, Dominique Fohr
2021	A	`conf`	Language Recognition on Unknown Conditions: The LORIA-Inria-MULTISPEECH System for AP20-OLR Challenge. Interspeech Raphaël Duroselle, Md. Sahidullah, Denis Jouvet, Irina Illina
2021	A	`conf`	Modeling and Training Strategies for Language Recognition Systems. Interspeech Raphaël Duroselle, Md. Sahidullah, Denis Jouvet, Irina Illina
2021	C	`conf`	Multiword Expression Features for Automatic Hate Speech Detection. NLDB Nicolas Zampieri, Irina Illina, Dominique Fohr
2021	—	`conf`	Unsupervised Domain Adaptation in Cross-corpora Abusive Language Detection. SocialNLP@NAACL Tulika Bose, Irina Illina, Dominique Fohr
2020	—	`conf`	Adaptation de domaine non supervisée pour la reconnaissance de la langue par régularisation d'un réseau de neurones (Unsupervised domain adaptation for language identification by regularization of a neural network). JEP-TALN-RECITAL (1) Raphaël Duroselle, Denis Jouvet, Irina Illina
2020	—	`conf`	BERT and fastText Embeddings for Automatic Detection of Toxic Speech. OCTA Ashwin Geet D'Sa, Irina Illina, Dominique Fohr
2020	J	`jnl`	DNN-Based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays. CoRR Nicolas Furnon, Romain Serizel, Irina Illina, Slim Essid
2020	J	`jnl`	DNN-Based Semantic Model for Rescoring N-best Speech Recognition List. CoRR Dominique Fohr, Irina Illina
2020	Misc	`conf`	DNN-based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays. ICASSP Nicolas Furnon, Romain Serizel, Irina Illina, Slim Essid
2020	—	`conf`	Introduction d'informations sémantiques dans un système de reconnaissance de la parole (Despite spectacular advances in recent years, the Automatic Speech Recognition (ASR) systems still make mistakes, especially in noisy environments). JEP-TALN-RECITAL (1) Stephane Level, Irina Illina, Dominique Fohr
2020	—	`conf`	Introduction of Semantic Model to Help Speech Recognition. TDS Stephane Level, Irina Illina, Dominique Fohr
2020	—	`conf`	Label Propagation-Based Semi-Supervised Learning for Hate Speech Classification. Insights Ashwin Geet D'Sa, Irina Illina, Dominique Fohr, Dietrich Klakow, Dana Ruiter
2020	A	`conf`	Metric Learning Loss Functions to Reduce Domain Mismatch in the x-Vector Space for Language Recognition. INTERSPEECH Raphaël Duroselle, Denis Jouvet, Irina Illina
2020	A	`conf`	On Semi-Supervised LF-MMI Training of Acoustic Models with Limited Data. INTERSPEECH Imran A. Sheikh, Emmanuel Vincent, Irina Illina
2020	—	`conf`	Reconnaissance automatique de la parole : génération des prononciations non natives pour l'enrichissement du lexique (In this study we propose a method for lexicon adaptation in order to improve the automatic speech recognition (ASR) of non-native speakers). JEP-TALN-RECITAL (1) Ismael Bada, Dominique Fohr, Irina Illina
2020	—	`conf`	Towards Non-Toxic Landscapes: Automatic Toxic Comment Detection Using DNN. TRAC@LREC Ashwin Geet D'Sa, Irina Illina, Dominique Fohr
2020	—	`conf`	Unsupervised Regularization of the Embedding Extractor for Robust Language Identification. Odyssey Raphaël Duroselle, Denis Jouvet, Irina Illina
2019	J	`jnl`	Towards non-toxic landscapes: Automatic toxic comment detection using DNN. CoRR Ashwin Geet D'Sa, Irina Illina, Dominique Fohr
2019	J	`jnl`	VoiceHome-2, an extended corpus for multichannel speech processing in real homes. Speech Commun. Nancy Bertin, Ewen Camberlein, Romain Lebarbenchon, Emmanuel Vincent, Sunit Sivasankaran, Irina Illina, Frédéric Bimbot
2018	J	`jnl`	DNN Uncertainty Propagation Using GMM-Derived Uncertainty Features for Noise Robust ASR. IEEE Signal Process. Lett. Karan Nathwani, Emmanuel Vincent, Irina Illina
2018	—	`conf`	Dynamic Extension of ASR Lexicon Using Wikipedia Data. SLT Badr Abdullah, Irina Illina, Dominique Fohr
2017	J	`jnl`	A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions. Comput. Speech Lang. Sunit Sivasankaran, Emmanuel Vincent, Irina Illina
2017	—	`conf`	An extended experimental investigation of DNN uncertainty propagation for noise robust ASR. HSCMA Karan Nathwani, Juan Andres Morales-Cordovilla, Sunit Sivasankaran, Irina Illina, Emmanuel Vincent
2017	C	`conf`	Consistent DNN uncertainty training and decoding for robust ASR. ASRU Karan Nathwani, Emmanuel Vincent, Irina Illina
2017	Misc	`conf`	Discriminative importance weighting of augmented training data for acoustic model training. ICASSP Sunit Sivasankaran, Emmanuel Vincent, Irina Illina
2017	J	`jnl`	Modelling Semantic Context of OOV Words in Large Vocabulary Continuous Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Imran A. Sheikh, Dominique Fohr, Irina Illina, Georges Linarès
2017	—	`conf`	RNN Language Model Estimation for Out-of-Vocabulary Words. LCT Irina Illina, Dominique Fohr
2017	C	`conf`	Topic segmentation in ASR transcripts using bidirectional RNNS for change detection. ASRU Imran A. Sheikh, Dominique Fohr, Irina Illina
2016	A	`conf`	A French Corpus for Distant-Microphone Speech Processing in Real Homes. INTERSPEECH Nancy Bertin, Ewen Camberlein, Emmanuel Vincent, Romain Lebarbenchon, Stéphane Peillon, Éric Lamande, Sunit Sivasankaran, Frédéric Bimbot, Irina Illina, Ariane Tom, Sylvain Fleury, Éric Jamet
2016	—	`conf`	Dynamic adjustment of language models for automatic speech recognition using word similarity. SLT Anna Currey, Irina Illina, Dominique Fohr
2016	B	`conf`	How Diachronic Text Corpora Affect Context based Retrieval of OOV Proper Names for Audio News. LREC Imran A. Sheikh, Irina Illina, Dominique Fohr
2016	A	`conf`	Improved Neural Bag-of-Words Model to Retrieve Out-of-Vocabulary Words in Speech Recognition. INTERSPEECH Imran A. Sheikh, Irina Illina, Dominique Fohr, Georges Linarès
2016	—	`conf`	Learning Word Importance with the Neural Bag-of-Words Model. Rep4NLP@ACL Imran A. Sheikh, Irina Illina, Dominique Fohr, Georges Linarès
2015	A	`conf`	Continuous word representation using neural networks for proper name retrieval from diachronic documents. INTERSPEECH Dominique Fohr, Irina Illina
2015	C	`conf`	Different word representations and their combination for proper name retrieval from diachronic documents. ASRU Irina Illina, Dominique Fohr
2015	B	`conf`	Experience of an International Collaborative Project with First Year Programming Students. COMPSAC James H. Paterson, Markku Karhu, Walter Cazzola, Irina Illina, Robert Law, Dario Machiodi, Marisa Maximiano, Catarina Silva
2015	J	`jnl`	Learning to retrieve out-of-vocabulary words in speech recognition. CoRR Imran A. Sheikh, Irina Illina, Dominique Fohr, Georges Linarès
2015	—	`conf`	Neural Networks Revisited for Proper Name Retrieval from Diachronic Documents. LTC Irina Illina, Dominique Fohr
2015	Misc	`conf`	OOV Proper Name retrieval using topic and lexical context models. ICASSP Imran A. Sheikh, Irina Illina, Dominique Fohr, Georges Linarès
2015	C	`conf`	Robust ASR using neural network based speech enhancement and feature simulation. ASRU Sunit Sivasankaran, Aditya Arie Nugraha, Emmanuel Vincent, Juan Andres Morales-Cordovilla, Siddharth Dalmia, Irina Illina, Antoine Liutkus
2015	A	`conf`	Study of entity-topic models for OOV proper name retrieval. INTERSPEECH Imran A. Sheikh, Irina Illina, Dominique Fohr
2014	J	`jnl`	Ajout de nouveaux noms propres au vocabulaire d'un système de transcription en utilisant un corpus diachronique. Trait. Autom. des Langues Irina Illina, Dominique Fohr, Georges Linarès
2014	—	`conf`	Proper name retrieval from diachronic documents for automatic speech transcription using lexical and temporal context. SLAM@INTERSPEECH Irina Illina, Dominique Fohr, Georges Linarès
2013	—	`conf`	Temporal and Lexical Context of Diachronic Text Documents for Automatic Out-Of-Vocabulary Proper Name Retrieval. LTC Irina Illina, Dominique Fohr, Georges Linarès, Imane Nkairi
2012	—	`conf`	Combining criteria for the detection of incorrect entries of non-native speech in the context of foreign language learning. SLT Luiza Orosanu, Denis Jouvet, Dominique Fohr, Irina Illina, Anne Bonneau
2012	—	`conf`	Détection de transcriptions incorrectes de parole non-native dans le cadre de l'apprentissage de langues étrangères (Detection of incorrect transcriptions of non-native speech in the context of foreign language learning) [in French]. JEP-TALN-RECITAL 2012 Luiza Orosanu, Denis Jouvet, Dominique Fohr, Irina Illina, Anne Bonneau
2012	Misc	`conf`	Evaluating grapheme-to-phoneme converters in automatic speech recognition context. ICASSP Denis Jouvet, Dominique Fohr, Irina Illina
2012	J	`jnl`	Gestion d'erreurs pour la fiabilisation des retours automatiques en apprentissage de la prosodie d'une langue seconde. Trait. Autom. des Langues Anne Bonneau, Dominique Fohr, Irina Illina, Denis Jouvet, Odile Mella, Larbi Mesbahi, Luiza Orosanu
2012	—	`conf`	Génération des prononciations de noms propres à l'aide des Champs Aléatoires Conditionnels (Pronunciation generation for proper names using Conditional Random Fields) [in French]. JEP-TALN-RECITAL 2012 Irina Illina, Dominique Fohr, Denis Jouvet
2012	J	`jnl`	Multilingual recognition of non-native speech using acoustic model transformation and pronunciation modeling. Int. J. Speech Technol. Ghazi Bouselmi, Dominique Fohr, Irina Illina
2011	A	`conf`	About Handling Boundary Uncertainty in a Speaking Rate Dependent Modeling Approach. INTERSPEECH Denis Jouvet, Dominique Fohr, Irina Illina
2011	A	`conf`	Grapheme-to-Phoneme Conversion Using Conditional Random Fields. INTERSPEECH Irina Illina, Dominique Fohr, Denis Jouvet
2011	—	`conf`	Reliability of non-native speech automatic segmentation for prosodic feedback. SLaTE Larbi Mesbahi, Denis Jouvet, Anne Bonneau, Dominique Fohr, Irina Illina, Yves Laprie
2010	J	`jnl`	A wavelet-based parameterization for speech/music discrimination. Comput. Speech Lang. E. Didiot, Irina Illina, Dominique Fohr, Odile Mella
2010	A	`conf`	Detailed pronunciation variant modeling for speech transcription. INTERSPEECH Denis Jouvet, Dominique Fohr, Irina Illina
2009	C	`conf`	Detection of OOV words by combining acoustic confidence measures with linguistic features. ASRU Frederik Stouten, Dominique Fohr, Irina Illina
2008	A	`conf`	Foreign accent identification based on prosodic parameters. INTERSPEECH Marina Piat, Dominique Fohr, Irina Illina
2008	A	`conf`	Multi-accent and accent-independent non-native speech recognition. INTERSPEECH Ghazi Bouselmi, Dominique Fohr, Irina Illina
2008	J	`jnl`	On-line Stochastic Matching compensation for non-stationary noise. Comput. Speech Lang. Vincent Barreaud, Irina Illina, Dominique Fohr
2007	J	`jnl`	Amélioration des Performances des Systèmes Automatiques de Reconnaissance de la Parole pour la Parole Non Native CoRR Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean Paul Haton
2007	J	`jnl`	Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition CoRR Ghazi Bouselmi, Dominique Fohr, Irina Illina
2007	A	`conf`	Combined acoustic and pronunciation modelling for non-native speech recognition. INTERSPEECH Ghazi Bouselmi, Dominique Fohr, Irina Illina
2007	J	`jnl`	Discriminative Phoneme Sequences Extraction for Non-Native Speaker's Origin Classification CoRR Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean Paul Haton
2007	—	`conf`	Discriminative phoneme sequence extraction for non-native speaker's origin classification. ISSPA Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean Paul Haton
2006	A	`conf`	A wavelet-based parameterization for speech/music segmentation. INTERSPEECH E. Didiot, Irina Illina, Odile Mella, Dominique Fohr, Jean Paul Haton
2006	—	`conf`	Fully Automated Non-Native Speech Recognition Using Confusion-Based Acoustic Model Integration and Graphemic Constraints. ICASSP (1) Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean-Paul Haton
2006	A	`conf`	Multilingual non-native speech recognition using phonetic confusion-based acoustic model modification and graphemic constraints. INTERSPEECH Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean Paul Haton
2006	—	`conf`	Speech/Music Discrimination Based on Wavelets for Broadcast Programs. SIGMAP E. Didiot, Irina Illina, Odile Mella, Dominique Fohr, Jean Paul Haton
2005	A	`conf`	Fully automated non-native speech recognition using confusion-based acoustic model integration. INTERSPEECH Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean Paul Haton
2004	A	`conf`	Experiments on the accuracy of phone models and liaison processing in a French broadcast news transcription system. INTERSPEECH Dominique Fohr, Odile Mella, Irina Illina, Christophe Cerisara
2004	A	`conf`	Exploiting models intrinsic robustness for noisy speech recognition. INTERSPEECH Christophe Cerisara, Dominique Fohr, Odile Mella, Irina Illina
2004	A	`conf`	Hidden factor dynamic Bayesian networks for speech recognition. INTERSPEECH Filip Korkmazsky, Murat Deviren, Dominique Fohr, Irina Illina
2004	A	`conf`	The automatic news transcription system: ANTS, some real time experiments. INTERSPEECH Dominique Fohr, Odile Mella, Christophe Cerisara, Irina Illina
2004	A	`conf`	Using linear interpolation to improve histogram equalization for speech recognition. INTERSPEECH Filip Korkmazsky, Dominique Fohr, Irina Illina
2003	—	`conf`	Combining EigenVoices and structural MLLR for speaker adaptation. ICASSP (1) Fabrice Lauri, Irina Illina, Dominique Fohr
2003	—	`conf`	On-line frame-synchronous compensation of non-stationary noise. ICASSP (1) Vincent Barreaud, Irina Illina, Dominique Fohr
2003	A	`conf`	Robust speech recognition to non-stationary noise based on model-driven approaches. INTERSPEECH Christophe Cerisara, Irina Illina
2003	A	`conf`	Structural state-based frame synchronous compensation. INTERSPEECH Vincent Barreaud, Irina Illina, Dominique Fohr, Filipp Korkmazsky
2003	A	`conf`	Using genetic algorithms for rapid speaker adaptation. INTERSPEECH Fabrice Lauri, Irina Illina, Dominique Fohr, Filipp Korkmazsky
2002	A	`conf`	Tree-structured maximum a posteriori adaptation for a segment-based speech recognition system. INTERSPEECH Irina Illina
1998	J	`jnl`	Assessing the importance of the segmentation probability in segment-based speech recognition. Speech Commun. Jan P. Verhasselt, Irina Illina, Jean-Pierre Martens, Yifan Gong, Jean Paul Haton
1998	J	`jnl`	Environment normalization training and environment adaptation using mixture stochastic trajectory model. Speech Commun. Irina Illina, Mohamed Afify, Yifan Gong
1997	Misc	`conf`	Elimination of trajectory folding phenomenon: HMM, trajectory mixture HMM and mixture stochastic trajectory model. ICASSP Irina Illina, Yifan Gong
1997	—	`—`	Extension du modèle stochastique des mélanges de trajectoires pour la reconnaissance automatique de la parole continue. Irina Illina
1997	—	`conf`	Speaker normalization training for mixture stochastic trajectory model. EUROSPEECH Irina Illina, Yifan Gong
1997	Misc	`conf`	The importance of segmentation probability in segment based speech recognizers. ICASSP Jan P. Verhasselt, Irina Illina, Jean-Pierre Martens, Yifan Gong, Jean-Paul Haton
1996	—	`conf`	Improvement in n-best search for continuous speech recognition. ICSLP Irina Illina, Yifan Gong
1996	—	`conf`	Modelling long term variability information in mixture stochastic trajectory framework. ICSLP Yifan Gong, Irina Illina, Jean Paul Haton
1996	—	`conf`	Stochastic trajectory model with state-mixture for continuous speech recognition. ICSLP Irina Illina, Yifan Gong