Felix Weninger

100 papers A* 4A 19B 4C 4Misc 22Journal 27Unranked 18

Year	Rank	Type	Title / Venue / Authors
2024	Misc	`conf`	Improving Speed/Accuracy Tradeoff for Online Streaming ASR via Real-Valued and Trainable Strides. ICASSP Dario Albesano, Nicola Ferri, Felix Weninger, Puming Zhan
2022	A	`conf`	Conformer with dual-mode chunked attention for joint online and offline ASR. INTERSPEECH Felix Weninger, Marco Gaudesi, Md. Akmal Haidar, Nicola Ferri, Jesús Andrés-Ferrer, Puming Zhan
2022	J	`jnl`	Holistic Affect Recognition Using PaNDA: Paralinguistic Non-Metric Dimensional Analysis. IEEE Trans. Affect. Comput. Yue Zhang, Felix Weninger, Björn W. Schuller, Rosalind W. Picard
2021	C	`conf`	ChannelAugment: Improving Generalization of Multi-Channel ASR by Training with Input Channel Randomization. ASRU Marco Gaudesi, Felix Weninger, Dushyant Sharma, Puming Zhan
2021	J	`jnl`	ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization. CoRR Marco Gaudesi, Felix Weninger, Dushyant Sharma, Puming Zhan
2021	C	`conf`	Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition. ASRU Felix Weninger, Marco Gaudesi, Ralf Leibold, Roberto Gemello, Puming Zhan
2021	J	`jnl`	Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition. CoRR Felix Weninger, Marco Gaudesi, Ralf Leibold, Roberto Gemello, Puming Zhan
2020	J	`jnl`	A Generic Human-Machine Annotation Framework Based on Dynamic Cooperative Learning. IEEE Trans. Cybern. Yue Zhang, Andrea Michi, Johannes Wagner, Elisabeth André, Björn W. Schuller, Felix Weninger
2020	B	`conf`	Dyadic Speech-based Affect Recognition using DAMI-P2C Parent-child Multimodal Interaction Dataset. ICMI Huili Chen, Yue Zhang, Felix Weninger, Rosalind W. Picard, Cynthia Breazeal, Hae Won Park
2020	J	`jnl`	Dyadic Speech-based Affect Recognition using DAMI-P2C Parent-child Multimodal Interaction Dataset. CoRR Huili Chen, Yue Zhang, Felix Weninger, Rosalind W. Picard, Cynthia Breazeal, Hae Won Park
2020	A	`conf`	Semi-Supervised Learning with Data Augmentation for End-to-End ASR. INTERSPEECH Felix Weninger, Franco Mana, Roberto Gemello, Jesús Andrés-Ferrer, Puming Zhan
2020	J	`jnl`	Semi-Supervised Learning with Data Augmentation for End-to-End ASR. CoRR Felix Weninger, Franco Mana, Roberto Gemello, Jesús Andrés-Ferrer, Puming Zhan
2020	J	`jnl`	openXDATA: A Tool for Multi-Target Data Generation and Missing Label Completion. CoRR Felix Weninger, Yue Zhang, Rosalind W. Picard
2019	J	`jnl`	Affective and behavioural computing: Lessons learnt from the First Computational Paralinguistics Challenge. Comput. Speech Lang. Björn W. Schuller, Felix Weninger, Yue Zhang, Fabien Ringeval, Anton Batliner, Stefan Steidl, Florian Eyben, Erik Marchi, Alessandro Vinciarelli, Klaus R. Scherer, Mohamed Chetouani, Marcello Mortillaro
2019	A	`conf`	Deep Learning Based Mandarin Accent Identification for Accent Robust ASR. INTERSPEECH Felix Weninger, Yang Sun, Junho Park, Daniel Willett, Puming Zhan
2019	A	`conf`	Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR. INTERSPEECH Felix Weninger, Jesús Andrés-Ferrer, Xinwei Li, Puming Zhan
2019	J	`jnl`	Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR. CoRR Felix Weninger, Jesús Andrés-Ferrer, Xinwei Li, Puming Zhan
2019	C	`conf`	Online Batch Normalization Adaptation for Automatic Speech Recognition. ASRU Franco Mana, Felix Weninger, Roberto Gemello, Puming Zhan
2018	J	`jnl`	Three recent trends in Paralinguistics on the way to omniscient machine intelligence. J. Multimodal User Interfaces Björn W. Schuller, Yue Zhang, Felix Weninger
2017	A*	`conf`	A Paralinguistic Approach To Speaker Diarisation: Using Age, Gender, Voice Likability and Personality Traits. ACM Multimedia Yue Zhang, Felix Weninger, Boqing Liu, Maximilian Schmitt, Florian Eyben, Björn W. Schuller
2017	A	`conf`	Cross-Domain Classification of Drowsiness in Speech: The Case of Alcohol Intoxication and Sleep Deprivation. INTERSPEECH Yue Zhang, Felix Weninger, Björn W. Schuller
2017	Misc	`conf`	Multi-task deep neural network with shared hidden layers: Breaking down the wall between emotion representations. ICASSP Yue Zhang, Yifan Liu, Felix Weninger, Björn W. Schuller
2017	B	`conf`	Towards intoxicated speech recognition. IJCNN Zixing Zhang, Felix Weninger, Martin Wöllmer, Jing Han, Björn W. Schuller
2016	A*	`conf`	Discriminatively Trained Recurrent Neural Networks for Continuous Dimensional Emotion Recognition from Audio. IJCAI Felix Weninger, Fabien Ringeval, Erik Marchi, Björn W. Schuller
2016	B	`conf`	Language proficiency assessment of English L2 speakers based on joint analysis of prosody and native language. ICMI Yue Zhang, Felix Weninger, Anton Batliner, Florian Hönig, Björn W. Schuller
2016	J	`jnl`	Route and Stopping Intent Prediction at Intersections From Car Fleet Data. IEEE Trans. Intell. Veh. Florian Groß, Justus Jordan, Felix Weninger, Felix Klanner, Björn W. Schuller
2016	A	`conf`	Sincerity and Deception in Speech: Two Sides of the Same Coin? A Transfer- and Multi-Task Learning Perspective. INTERSPEECH Yue Zhang, Felix Weninger, Zhao Ren, Björn W. Schuller
2015	J	`jnl`	A Survey on perceived speaker traits: Personality, likability, pathology, and the first challenge. Comput. Speech Lang. Björn W. Schuller, Stefan Steidl, Anton Batliner, Elmar Nöth, Alessandro Vinciarelli, Felix Burkhardt, Rob van Son, Felix Weninger, Florian Eyben, Tobias Bocklet, Gelareh Mohammadi, Benjamin Weiss
2015	Misc	`conf`	Deep NMF for speech separation. ICASSP Jonathan Le Roux, John R. Hershey, Felix Weninger
2015	—	`—`	Intelligent Single-Channel Methods for Multi-Source Audio Analysis. Felix Weninger
2015	J	`jnl`	Introducing CURRENNT: the munich open-source CUDA recurrent neural network toolkit. J. Mach. Learn. Res. Felix Weninger, Johannes Bergmann, Björn W. Schuller
2015	B	`conf`	Non-linear prediction with LSTM recurrent neural networks for acoustic novelty detection. IJCNN Erik Marchi, Fabio Vesperini, Felix Weninger, Florian Eyben, Stefano Squartini, Björn W. Schuller
2015	—	`conf`	Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR. LVA/ICA Felix Weninger, Hakan Erdogan, Shinji Watanabe, Emmanuel Vincent, Jonathan Le Roux, John R. Hershey, Björn W. Schuller
2015	A	`conf`	The INTERSPEECH 2015 computational paralinguistics challenge: nativeness, parkinson's & eating condition. INTERSPEECH Björn W. Schuller, Stefan Steidl, Anton Batliner, Simone Hantke, Florian Hönig, Juan Rafael Orozco-Arroyave, Elmar Nöth, Yue Zhang, Felix Weninger
2014	J	`jnl`	A Broadcast News Corpus for Evaluation and Tuning of German LVCSR Systems. CoRR Felix Weninger, Björn W. Schuller, Florian Eyben, Martin Wöllmer, Gerhard Rigoll
2014	J	`jnl`	Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures. CoRR John R. Hershey, Jonathan Le Roux, Felix Weninger
2014	Misc	`conf`	Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition. ICASSP Felix Weninger, Shinji Watanabe, Yuuki Tachioka, Björn W. Schuller
2014	A	`conf`	Discriminative NMF and its application to single-channel source separation. INTERSPEECH Felix Weninger, Jonathan Le Roux, John R. Hershey, Shinji Watanabe
2014	—	`conf`	Discriminatively trained recurrent neural networks for single-channel speech separation. GlobalSIP Felix Weninger, John R. Hershey, Jonathan Le Roux, Björn W. Schuller
2014	A*	`conf`	Emotional Analysis of Music: A Comparison of Methods. ACM Multimedia Mohammad Soleymani, Anna Aljanaki, Yi-Hsuan Yang, Michael N. Caro, Florian Eyben, Konstantin Markov, Björn W. Schuller, Remco C. Veltkamp, Felix Weninger, Frans Wiering
2014	J	`jnl`	Feature enhancement by deep LSTM networks for ASR in reverberant multisource environments. Comput. Speech Lang. Felix Weninger, Jürgen T. Geiger, Martin Wöllmer, Björn W. Schuller, Gerhard Rigoll
2014	J	`jnl`	Medium-term speaker states - A review on intoxication, sleepiness and the first challenge. Comput. Speech Lang. Björn W. Schuller, Stefan Steidl, Anton Batliner, Florian Schiel, Jarek Krajewski, Felix Weninger, Florian Eyben
2014	J	`jnl`	Memory-Enhanced Neural Networks and NMF for Robust ASR. IEEE ACM Trans. Audio Speech Lang. Process. Jürgen T. Geiger, Felix Weninger, Jort F. Gemmeke, Martin Wöllmer, Björn W. Schuller, Gerhard Rigoll
2014	—	`conf`	On-Line NMF-Based Stereo Up-Mixing of Speech Improves Perceived Reduction of Non-Stationary Noise. Semantic Audio Christian Kirst, Felix Weninger, Cyril Joder, Peter Grosche, Jürgen T. Geiger, Björn W. Schuller
2014	Misc	`conf`	On-line continuous-time music mood regression with deep recurrent neural networks. ICASSP Felix Weninger, Florian Eyben, Björn W. Schuller
2014	A	`conf`	Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modelling. INTERSPEECH Jürgen T. Geiger, Zixing Zhang, Felix Weninger, Björn W. Schuller, Gerhard Rigoll
2014	Misc	`conf`	Single-channel speech separation with memory-enhanced recurrent neural networks. ICASSP Felix Weninger, Florian Eyben, Björn W. Schuller
2014	—	`conf`	The Munich LSTM-RNN Approach to the MediaEval 2014 "Emotion in Music'" Task. MediaEval Eduardo Coutinho, Felix Weninger, Björn W. Schuller, Klaus R. Scherer
2013	Misc	`conf`	A comparative study on sparsity penalties for NMF-based speech separation: Beyond LP-norms. ICASSP Cyril Joder, Felix Weninger, David Virette, Björn W. Schuller
2013	Misc	`conf`	A discriminative approach to polyphonic piano note transcription using supervised non-negative matrix factorization. ICASSP Felix Weninger, Christian Kirst, Björn W. Schuller, Hans-Joachim Bungartz
2013	A	`conf`	Affect recognition in real-life acoustic conditions - a new perspective on feature selection. INTERSPEECH Florian Eyben, Felix Weninger, Björn W. Schuller
2013	Misc	`conf`	Feature enhancement by bidirectional LSTM networks for conversational speech recognition in highly non-stationary noise. ICASSP Martin Wöllmer, Zixing Zhang, Felix Weninger, Björn W. Schuller, Gerhard Rigoll
2013	—	`conf`	Influence of Low-Level Features Extracted from Rhythmic and Harmonic Sections on Music Genre Classification. ICMMI Aldona Rosner, Felix Weninger, Björn W. Schuller, Marcin Michalak, Bozena Kostek
2013	Misc	`conf`	Integrating noise estimation and factorization-based speech separation: A novel hybrid approach. ICASSP Cyril Joder, Felix Weninger, David Virette, Björn W. Schuller
2013	—	`conf`	Likability of human voices: A feature analysis and a neural network regression approach to automatic likability estimation. WIAMIS Florian Eyben, Felix Weninger, Erik Marchi, Björn W. Schuller
2013	J	`jnl`	Noise robust ASR in reverberated multisource environments applying convolutive NMF and Long Short-Term Memory. Comput. Speech Lang. Martin Wöllmer, Felix Weninger, Jürgen T. Geiger, Björn W. Schuller, Gerhard Rigoll
2013	Misc	`conf`	Real-life voice activity detection with LSTM Recurrent Neural Networks and an application to Hollywood movies. ICASSP Florian Eyben, Felix Weninger, Stefano Squartini, Björn W. Schuller
2013	A*	`conf`	Recent developments in openSMILE, the munich open-source multimedia feature extractor. ACM Multimedia Florian Eyben, Felix Weninger, Florian Groß, Björn W. Schuller
2013	J	`jnl`	Serious Gaming for Behavior Change: The State of Play. IEEE Pervasive Comput. Björn W. Schuller, Ian Dunwell, Felix Weninger, Lucas Paletta
2013	Misc	`conf`	Speaker trait characterization in web videos: Uniting speech, language, and facial features. ICASSP Felix Weninger, Claudia Wagner, Martin Wöllmer, Björn W. Schuller, Louis-Philippe Morency
2013	A	`conf`	The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. INTERSPEECH Björn W. Schuller, Stefan Steidl, Anton Batliner, Alessandro Vinciarelli, Klaus R. Scherer, Fabien Ringeval, Mohamed Chetouani, Felix Weninger, Florian Eyben, Erik Marchi, Marcello Mortillaro, Hugues Salamin, Anna Polychroniou, Fabio Valente, Samuel Kim
2013	—	`conf`	The TUM Approach to the MediaEval Music Emotion Task Using Generic Affective Audio Features. MediaEval Felix Weninger, Florian Eyben, Björn W. Schuller
2013	—	`conf`	The acoustics of eye contact: detecting visual attention from conversational audio cues. GazeIn@ICMI Florian Eyben, Felix Weninger, Lucas Paletta, Björn W. Schuller
2013	J	`jnl`	Words that Fascinate the Listener: Predicting Affective Ratings of On-Line Lectures. Int. J. Distance Educ. Technol. Felix Weninger, Pascal Staudt, Björn W. Schuller
2013	J	`jnl`	YouTube Movie Reviews: Sentiment Analysis in an Audio-Visual Context. IEEE Intell. Syst. Martin Wöllmer, Felix Weninger, Tobias Knaup, Björn W. Schuller, Congkai Sun, Kenji Sagae, Louis-Philippe Morency
2012	Misc	`conf`	Automatic recognition of emotion evoked by general sound events. ICASSP Björn W. Schuller, Simone Hantke, Felix Weninger, Wenjing Han, Zixing Zhang, Shrikanth S. Narayanan
2012	A	`conf`	Combining Bottleneck-BLSTM and Semi-Supervised Sparse NMF for Recognition of Conversational Speech in Highly Instationary Noise. INTERSPEECH Felix Weninger, Martin Wöllmer, Björn W. Schuller
2012	A	`conf`	Discrimination of Linguistic and Non-Linguistic Vocalizations in Spontaneous Speech: Intra- and Inter-Corpus Perspectives. INTERSPEECH Felix Weninger, Björn W. Schuller
2012	—	`conf`	Fully Automatic Audiovisual Emotion Recognition: Voice, Words, and the Face. ITG Conference on Speech Communication Martin Wöllmer, Moritz Kaiser, Florian Eyben, Felix Weninger, Björn W. Schuller, Gerhard Rigoll
2012	A	`conf`	Improving Recognition of Speaker States and Traits by Cumulative Evidence: Intoxication, Sleepiness, Age and Gender. INTERSPEECH Felix Weninger, Erik Marchi, Björn W. Schuller
2012	—	`ch.`	Music Information Retrieval: An Inspirational Guide to Transfer from Related Disciplines. Multimodal Music Processing Felix Weninger, Björn W. Schuller, Cynthia C. S. Liem, Frank Kurth, Alan Hanjalic
2012	Misc	`conf`	Non-negative matrix factorization for highly noise-robust ASR: To enhance or to recognize? ICASSP Felix Weninger, Martin Wöllmer, Jürgen T. Geiger, Björn W. Schuller, Jort F. Gemmeke, Antti Hurmalainen, Tuomas Virtanen, Gerhard Rigoll
2012	J	`jnl`	Optimization and Parallelization of Monaural Source Separation Algorithms in the openBliSSART Toolkit. J. Signal Process. Syst. Felix Weninger, Björn W. Schuller
2012	—	`conf`	Real-Time Speech Separation by Semi-supervised Nonnegative Matrix Factorization. LVA/ICA Cyril Joder, Felix Weninger, Florian Eyben, David Virette, Björn W. Schuller
2012	Misc	`conf`	Robust feature extraction for automatic recognition of vibrato singing in recorded polyphonic music. ICASSP Felix Weninger, Noam Amir, Ofer Amir, Irit Ronen, Florian Eyben, Björn W. Schuller
2012	—	`conf`	Sparse, Hierarchical and Semi-Supervised Base Learning for Monaural Enhancement of Conversational Speech. ITG Conference on Speech Communication Felix Weninger, Martin Wöllmer, Björn W. Schuller
2012	Misc	`conf`	Supervised and semi-supervised suppression of background music in monaural speech recordings. ICASSP Felix Weninger, Jordi Feliu, Björn W. Schuller
2012	J	`jnl`	Synthesized speech for model training in cross-corpus recognition of human emotion. Int. J. Speech Technol. Björn W. Schuller, Zixing Zhang, Felix Weninger, Felix Burkhardt
2012	A	`conf`	The INTERSPEECH 2012 Speaker Trait Challenge. INTERSPEECH Björn W. Schuller, Stefan Steidl, Anton Batliner, Elmar Nöth, Alessandro Vinciarelli, Felix Burkhardt, Rob van Son, Felix Weninger, Florian Eyben, Tobias Bocklet, Gelareh Mohammadi, Benjamin Weiss
2012	J	`jnl`	The Voice of Leadership: Models and Performances of Automatic Analysis in Online Speeches. IEEE Trans. Affect. Comput. Felix Weninger, Jarek Krajewski, Anton Batliner, Björn W. Schuller
2012	—	`conf`	Towards Automatic Intoxication Detection from Speech in Real-Life Acoustic Environments. ITG Conference on Speech Communication Zixing Zhang, Felix Weninger, Björn W. Schuller
2012	—	`conf`	Towards distributed recognition of emotion from speech. ISCCSP Wenjing Han, Zixing Zhang, Jun Deng, Martin Wöllmer, Felix Weninger, Björn W. Schuller
2012	—	`conf`	Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature Sets. MediaEval Florian Eyben, Felix Weninger, Nicolas H. Lehment, Gerhard Rigoll, Björn W. Schuller
2011	A	`conf`	"Would You Buy a Car from Me?" - On the Likability of Telephone Voices. INTERSPEECH Felix Burkhardt, Björn W. Schuller, Benjamin Weiss, Felix Weninger
2011	A	`conf`	Acoustic-Linguistic Recognition of Interest in Speech with Bottleneck-BLSTM Nets. INTERSPEECH Martin Wöllmer, Felix Weninger, Florian Eyben, Björn W. Schuller
2011	Misc	`conf`	Audio recognition in the wild: Static and dynamic classification on a real-world database of animal vocalizations. ICASSP Felix Weninger, Björn W. Schuller
2011	—	`conf`	Automatic Assessment of Singer Traits in Popular Music: Gender, Age, Height and Race. ISMIR Felix Weninger, Martin Wöllmer, Björn W. Schuller
2011	Misc	`conf`	Combining monaural source separation with Long Short-Term Memory for increased robustness in vocalist gender recognition. ICASSP Felix Weninger, Jean-Louis Durrieu, Florian Eyben, Gaël Richard, Björn W. Schuller
2011	J	`jnl`	Computational Assessment of Interest in Speech - Facing the Real-Life Challenge. Künstliche Intell. Martin Wöllmer, Felix Weninger, Florian Eyben, Björn W. Schuller
2011	Misc	`conf`	Localization of non-linguistic events in spontaneous speech by Non-Negative Matrix Factorization and Long Short-Term Memory. ICASSP Felix Weninger, Björn W. Schuller, Martin Wöllmer, Gerhard Rigoll
2011	—	`conf`	Multi-Modal Non-Prototypical Music Mood Analysis in Continuous Space: Reliability and Performances. ISMIR Björn W. Schuller, Felix Weninger, Johannes Dorfner
2011	Misc	`conf`	OpenBliSSART: Design and evaluation of a research toolkit for Blind Source Separation in Audio Recognition Tasks. ICASSP Felix Weninger, Alexander Lehmann, Björn W. Schuller
2011	J	`jnl`	Recognition of Nonprototypical Emotions in Reverberated and Noisy Speech by Nonnegative Matrix Factorization. EURASIP J. Adv. Signal Process. Felix Weninger, Björn W. Schuller, Anton Batliner, Stefan Steidl, Dino Seppi
2011	A	`conf`	Speech-Based Non-Prototypical Affect Recognition for Child-Robot Interaction in Reverberated Environments. INTERSPEECH Martin Wöllmer, Felix Weninger, Stefan Steidl, Anton Batliner, Björn W. Schuller
2011	—	`conf`	Ten Recent Trends in Computational Paralinguistics. COST 2102 Training School Björn W. Schuller, Felix Weninger
2011	C	`conf`	Unsupervised learning in cross-corpus acoustic emotion recognition. ASRU Zixing Zhang, Felix Weninger, Martin Wöllmer, Björn W. Schuller
2011	A	`conf`	Using Multiple Databases for Training in Emotion Recognition: To Unite or to Vote? INTERSPEECH Björn W. Schuller, Zixing Zhang, Felix Weninger, Gerhard Rigoll
2010	Misc	`conf`	Discrimination of speech and non-linguistic vocalizations by Non-Negative Matrix Factorization. ICASSP Björn W. Schuller, Felix Weninger
2010	Misc	`conf`	Non-negative matrix factorization as noise-robust feature extractor for speech recognition. ICASSP Björn W. Schuller, Felix Weninger, Martin Wöllmer, Yang Sun, Gerhard Rigoll
2010	—	`conf`	Vocalist Gender Recognition in Recorded Popular Music. ISMIR Björn W. Schuller, Christoph Kozielski, Felix Weninger, Florian Eyben, Gerhard Rigoll