F
Felix Weninger
Researcher at Nuance Communications
Publications - 124
Citations - 7455
Felix Weninger is an academic researcher from Nuance Communications. The author has contributed to research in topics: Recurrent neural network & Non-negative matrix factorization. The author has an hindex of 35, co-authored 123 publications receiving 6444 citations. Previous affiliations of Felix Weninger include Mitsubishi & Technische Universität München.
Papers
More filters
Proceedings ArticleDOI
Recent developments in openSMILE, the munich open-source multimedia feature extractor
TL;DR: OpenSMILE 2.0 as mentioned in this paper unifies feature extraction paradigms from speech, music, and general sound events with basic video features for multi-modal processing, allowing for time synchronization of parameters, on-line incremental processing as well as off-line and batch processing, and the extraction of statistical functionals (feature summaries).
Proceedings ArticleDOI
The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism
Björn 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 +14 more
TL;DR: The INTERSPEECH 2013 Computational Paralinguistics Challenge provides for the first time a unified test-bed for Social Signals such as laughter in speech and introduces conflict in group discussions as a new task and deals with autism and its manifestations in speech.
Book ChapterDOI
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
Felix Weninger,Hakan Erdogan,Shinji Watanabe,Emmanuel Vincent,Jonathan Le Roux,John R. Hershey,Björn Schuller +6 more
TL;DR: It is demonstrated that LSTM speech enhancement, even when used 'naively' as front-end processing, delivers competitive results on the CHiME-2 speech recognition task.
Posted Content
Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
TL;DR: This work starts with a model-based approach and an associated inference algorithm, and folds the inference iterations as layers in a deep network, and shows how this framework allows to interpret conventional networks as mean-field inference in Markov random fields, and to obtain new architectures by instead using belief propagation as the inference algorithm.
Journal ArticleDOI
YouTube Movie Reviews: Sentiment Analysis in an Audio-Visual Context
TL;DR: Experimental results indicate that training on written movie reviews is a promising alternative to exclusively using (spoken) in-domain data for building a system that analyzes spoken movie review videos, and that language-independent audio-visual analysis can compete with linguistic analysis.