What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
His primary areas of study are Artificial intelligence, Speech recognition, Natural language processing, Hidden Markov model and French.
His Artificial intelligence study combines topics in areas such as Computer vision and Pattern recognition.
His Speech recognition research is multidisciplinary, relying on both Artificial neural network, Segmentation, Word and Support vector machine.
The various areas that Guillaume Gravier examines in his Natural language processing study include Speaker diarisation and Audio mining.
His work carried out in the field of Speaker diarisation brings together such families of science as Normalization and Cluster analysis.
Guillaume Gravier studied Hidden Markov model and Audio-visual speech recognition that intersect with Facial recognition system, Usability, Feature extraction and Speechreading.
His most cited work include:
- A tutorial on text-independent speaker verification (698 citations)
- Recent advances in the automatic recognition of audiovisual speech (614 citations)
- The ESTER Phase II Evaluation Campaign for the Rich Transcription of French Broadcast News (202 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Speech recognition, Natural language processing, Pattern recognition and Multimedia.
His studies in Artificial intelligence integrate themes in fields like Machine learning and Computer vision.
The Speech recognition study combines topics in areas such as Search engine indexing and Robustness.
His Natural language processing study combines topics from a wide range of disciplines, such as Transcription and Word.
His work is dedicated to discovering how Pattern recognition, Cluster analysis are connected with Unsupervised learning and other disciplines.
His Multimedia study also includes
- Hyperlink together with TRECVID,
- World Wide Web and related Information retrieval.
He most often published in these fields:
- Artificial intelligence (64.37%)
- Speech recognition (36.25%)
- Natural language processing (26.88%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (64.37%)
- Hyperlink (13.13%)
- Artificial neural network (11.88%)
In recent papers he was focusing on the following fields of study:
Guillaume Gravier spends much of his time researching Artificial intelligence, Hyperlink, Artificial neural network, Multimedia and Information retrieval.
Guillaume Gravier has included themes like Machine learning and Natural language processing in his Artificial intelligence study.
His work on Conditional random field as part of general Natural language processing research is frequently linked to Label propagation, thereby connecting diverse disciplines of science.
Guillaume Gravier works mostly in the field of Artificial neural network, limiting it down to concerns involving Convolutional neural network and, occasionally, Optical flow and Computer vision.
His research in Multimedia focuses on subjects like World Wide Web, which are connected to Big data.
The Relevance research Guillaume Gravier does as part of his general Information retrieval study is frequently linked to other disciplines of science, such as RDF, therefore creating a link between diverse domains of science.
Between 2015 and 2021, his most popular works were:
- One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network (35 citations)
- One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network (35 citations)
- Bidirectional Joint Representation Learning with Symmetrical Deep Neural Networks for Multimodal and Crossmodal Applications (26 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Guillaume Gravier mainly focuses on Artificial intelligence, Artificial neural network, Deep learning, Crossmodal and Feature learning.
His studies deal with areas such as Motion, Convolutional neural network and Anticipation as well as Artificial neural network.
His Convolutional neural network research is multidisciplinary, incorporating perspectives in Optical flow, Robot, Video tracking and Computer vision.
The study incorporates disciplines such as Sentence, Spoken language, Natural language processing, Word and Dialog box in addition to Deep learning.
Guillaume Gravier has researched Feature learning in several fields, including Class and Ensemble learning.
His Autoencoder research includes elements of Word2vec, Embedding, Speech recognition, Query expansion and Pattern recognition.
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.
