What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Machine learning
His primary areas of investigation include Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Artificial neural network.
Hervé Bourlard has included themes like Posterior probability and Robustness in his Speech recognition study.
His Artificial intelligence research includes themes of Machine learning and Natural language processing.
His work deals with themes such as Connectionism, Speaker recognition, Vocabulary, Linear discriminant analysis and Multilayer perceptron, which intersect with Hidden Markov model.
His research in Pattern recognition tackles topics such as Computer vision which are related to areas like Support vector machine.
His Artificial neural network research includes elements of Language model and Context, Context model.
His most cited work include:
- Connectionist Speech Recognition: A Hybrid Approach (1040 citations)
- Auto-association by multilayer perceptrons and singular value decomposition (870 citations)
- Social Signal Processing (705 citations)
What are the main themes of his work throughout his whole career to date?
Hervé Bourlard mainly investigates Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Artificial neural network.
His work investigates the relationship between Speech recognition and topics such as Posterior probability that intersect with problems in Phone.
His research in Artificial intelligence intersects with topics in Machine learning and Natural language processing.
His Hidden Markov model study combines topics from a wide range of disciplines, such as Context, Connectionism, Hybrid system, Markov model and Mixture model.
His Pattern recognition research is multidisciplinary, incorporating perspectives in Cluster analysis and Robustness.
He mostly deals with Time delay neural network in his studies of Artificial neural network.
He most often published in these fields:
- Speech recognition (78.78%)
- Artificial intelligence (59.03%)
- Hidden Markov model (40.34%)
What were the highlights of his more recent work (between 2014-2021)?
- Speech recognition (78.78%)
- Artificial intelligence (59.03%)
- Artificial neural network (20.17%)
In recent papers he was focusing on the following fields of study:
Hervé Bourlard mostly deals with Speech recognition, Artificial intelligence, Artificial neural network, Pattern recognition and Hidden Markov model.
His Speech recognition research incorporates elements of Context and Subspace topology.
His studies deal with areas such as Machine learning and Natural language processing as well as Artificial intelligence.
The various areas that Hervé Bourlard examines in his Artificial neural network study include Template matching and Compressed sensing.
His study looks at the relationship between Pattern recognition and topics such as Posterior probability, which overlap with k-nearest neighbors algorithm.
The concepts of his Hidden Markov model study are interwoven with issues in Word error rate, Noise, Markov model, Mixture model and Principal component analysis.
Between 2014 and 2021, his most popular works were:
- Social Signal Processing (705 citations)
- An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation (26 citations)
- Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model (22 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Hervé Bourlard focuses on Speech recognition, Artificial intelligence, Artificial neural network, Pattern recognition and Hidden Markov model.
His biological study spans a wide range of topics, including Connectionism and Dropout.
The Artificial intelligence study combines topics in areas such as Social computing, Turn-taking and Natural language processing.
His work in Artificial neural network addresses subjects such as Template matching, which are connected to disciplines such as Feature extraction, Pattern matching and Feature vector.
His work carried out in the field of Pattern recognition brings together such families of science as Subspace topology, Posterior probability, Distance matrix and Compressed sensing.
His Hidden Markov model research integrates issues from Context and Machine learning.
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.
