What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Linguistics
- Speech recognition
His primary areas of investigation include Speech recognition, Artificial intelligence, Natural language processing, Speech processing and Speaker recognition.
His study in the fields of Transcription, Speaker diarisation, Word error rate and Voice activity detection under the domain of Speech recognition overlaps with other disciplines such as Sound detection.
While the research belongs to areas of Transcription, he spends his time largely on the problem of NIST, intersecting his research to questions surrounding Segmentation.
His study in the field of Word also crosses realms of Resource.
His Natural language processing study combines topics in areas such as Speech corpus and Languages of Africa.
His Speaker recognition research includes elements of Feature extraction, Motion compensation, TIMIT and Noise.
His most cited work include:
- Automatic speech recognition for under-resourced languages: A survey (243 citations)
- The zero resource speech challenge 2017 (123 citations)
- Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation (116 citations)
What are the main themes of his work throughout his whole career to date?
Laurent Besacier mainly investigates Artificial intelligence, Speech recognition, Natural language processing, Machine translation and Language model.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Machine learning and Pattern recognition.
The Speech recognition study combines topics in areas such as Segmentation and Speech translation.
His work carried out in the field of Natural language processing brings together such families of science as Pronunciation, Context, Speech corpus and Languages of Africa.
Laurent Besacier has researched Machine translation in several fields, including Decoding methods and Rule-based machine translation.
Laurent Besacier usually deals with Language model and limits it to topics linked to Acoustic model and Voice activity detection.
He most often published in these fields:
- Artificial intelligence (55.33%)
- Speech recognition (50.41%)
- Natural language processing (45.90%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (55.33%)
- Speech recognition (50.41%)
- Natural language processing (45.90%)
In recent papers he was focusing on the following fields of study:
Laurent Besacier mainly focuses on Artificial intelligence, Speech recognition, Natural language processing, Word and Machine translation.
Artificial intelligence is closely attributed to Machine learning in his work.
His research on Speech recognition focuses in particular on Language model.
Laurent Besacier has included themes like Similarity and Zero in his Natural language processing study.
His Word research incorporates themes from Context, Segmentation and Syllable.
His studies deal with areas such as Decoding methods and Image retrieval as well as Machine translation.
Between 2016 and 2021, his most popular works were:
- The zero resource speech challenge 2017 (123 citations)
- End-to-End Automatic Speech Translation of Audiobooks (79 citations)
- FlauBERT: Unsupervised Language Model Pre-training for French (32 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Linguistics
- Programming language
His main research concerns Artificial intelligence, Natural language processing, Speech recognition, Word and Sentence.
His Artificial intelligence study incorporates themes from State and Pattern recognition.
Natural language processing is represented through his Parsing and Language model research.
His Speech recognition research includes themes of End-to-end principle and Speech translation.
His studies in End-to-end principle integrate themes in fields like Transcription, Decoding methods, Training set and Target text.
His Sentence research is multidisciplinary, incorporating elements of Plagiarism detection, Word-sense disambiguation, Similarity, Contextualization and French.
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.
