What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Speech recognition
Lukas Burget spends much of his time researching Speech recognition, Artificial intelligence, NIST, Pattern recognition and Word error rate.
His Speech recognition study combines topics from a wide range of disciplines, such as Mixture model, Discriminative model and Support vector machine.
He has included themes like Subspace topology and Subspace Gaussian Mixture Model in his Mixture model study.
Lukas Burget combines topics linked to Natural language processing with his work on Artificial intelligence.
His work on Speaker recognition and Feature extraction as part of his general Pattern recognition study is frequently connected to Waveform, thereby bridging the divide between different branches of science.
Lukas Burget has researched Language model in several fields, including Machine learning, Recurrent neural network, Time delay neural network and Reduction.
His most cited work include:
- The Kaldi Speech Recognition Toolkit (3765 citations)
- Recurrent neural network based language model (3552 citations)
- Extensions of recurrent neural network language model (1183 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Speech recognition, Artificial intelligence, NIST, Pattern recognition and Speaker recognition.
Lukas Burget combines subjects such as Artificial neural network and Feature extraction with his study of Speech recognition.
The concepts of his Artificial intelligence study are interwoven with issues in Machine learning and Natural language processing.
The NIST study combines topics in areas such as Feature, Support vector machine and Language identification.
His Mixture model study, which is part of a larger body of work in Pattern recognition, is frequently linked to Gaussian process, bridging the gap between disciplines.
His work on Speaker verification as part of general Speaker recognition study is frequently linked to Adaptation, bridging the gap between disciplines.
He most often published in these fields:
- Speech recognition (74.69%)
- Artificial intelligence (50.61%)
- NIST (26.53%)
What were the highlights of his more recent work (between 2018-2021)?
- Speech recognition (74.69%)
- Artificial intelligence (50.61%)
- Hidden Markov model (14.69%)
In recent papers he was focusing on the following fields of study:
Lukas Burget mainly investigates Speech recognition, Artificial intelligence, Hidden Markov model, Speaker recognition and Speaker diarisation.
His Speech recognition research integrates issues from Artificial neural network and Embedding.
His studies deal with areas such as Mixture model and Speech processing as well as Artificial neural network.
His Artificial intelligence research incorporates elements of Natural language processing, Machine learning and Pattern recognition.
His work deals with themes such as Covariance and SemEval, which intersect with Natural language processing.
His research in Speaker recognition intersects with topics in NIST and End-to-end principle.
Between 2018 and 2021, his most popular works were:
- SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures (42 citations)
- How to Improve Your Speaker Embeddings Extractor in Generic Toolkits (34 citations)
- Bayesian HMM Based x-Vector Clustering for Speaker Diarization. (30 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His scientific interests lie mostly in Speech recognition, Hidden Markov model, Artificial intelligence, Speaker diarisation and Bayesian probability.
Speech recognition is closely attributed to End-to-end principle in his study.
His work carried out in the field of Hidden Markov model brings together such families of science as Artificial neural network and Speech processing.
In his research, SemEval is intimately related to Natural language processing, which falls under the overarching field of Artificial intelligence.
His research integrates issues of Inference, Prior probability and Cluster analysis in his study of Speaker diarisation.
His work in Speaker recognition covers topics such as NIST which are related to areas like Autoencoder, Preprocessor and Noise reduction.
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.
