What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
Felix Weninger spends much of his time researching Speech recognition, Artificial intelligence, Recurrent neural network, Speech processing and Pattern recognition.
The various areas that he examines in his Speech recognition study include Cognitive psychology and Noise.
His Artificial intelligence study combines topics in areas such as Matrix decomposition and Natural language processing.
His Recurrent neural network study incorporates themes from Time delay neural network, Speech enhancement, Task and Word error rate.
The Speech processing study combines topics in areas such as Feature, Feature vector, Context awareness, Pragmatics and Visualization.
His study in Pattern recognition is interdisciplinary in nature, drawing from both Non-negative matrix factorization and Source separation.
His most cited work include:
- Recent developments in openSMILE, the munich open-source multimedia feature extractor (800 citations)
- Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR (363 citations)
- The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism (351 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Pattern recognition, Recurrent neural network and Non-negative matrix factorization.
His work deals with themes such as Speech enhancement, Feature extraction and Feature, which intersect with Speech recognition.
His Artificial intelligence research incorporates themes from Matrix decomposition and Natural language processing.
His Pattern recognition research includes elements of Autoencoder and Conversational speech.
His Recurrent neural network research is multidisciplinary, relying on both Time delay neural network, Valence and Test set.
His research investigates the connection between Non-negative matrix factorization and topics such as Source separation that intersect with issues in Blind signal separation and Singing.
He most often published in these fields:
- Speech recognition (67.48%)
- Artificial intelligence (47.97%)
- Pattern recognition (30.89%)
What were the highlights of his more recent work (between 2016-2020)?
- Speech recognition (67.48%)
- Artificial intelligence (47.97%)
- Pattern recognition (30.89%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Speech recognition, Artificial intelligence, Pattern recognition, Word error rate and Affect.
The study incorporates disciplines such as Paralanguage and Artificial neural network in addition to Speech recognition.
His work focuses on many connections between Artificial neural network and other disciplines, such as Fuzzy logic, that overlap with his field of interest in Emotion recognition.
His work in Artificial intelligence addresses issues such as Natural language processing, which are connected to fields such as Set.
His research in Pattern recognition intersects with topics in End-to-end principle and Regularization.
The concepts of his Affect study are interwoven with issues in Context, Non metric, Variation, Speech corpus and Hidden Markov model.
Between 2016 and 2020, his most popular works were:
- Multi-task deep neural network with shared hidden layers: Breaking down the wall between emotion representations (23 citations)
- Affective and Behavioural Computing: Lessons Learnt from the First Computational Paralinguistics Challenge (12 citations)
- Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR (9 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
His primary scientific interests are in Speech recognition, Artificial intelligence, Artificial neural network, Emotion recognition and Fuzzy logic.
His Speech recognition research is multidisciplinary, incorporating perspectives in Adaptation and Robustness.
His Artificial intelligence research is multidisciplinary, incorporating elements of Stress, Mandarin Chinese and Identification.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
