What is he best known for?
The fields of study he is best known for:
- Linguistics
- Artificial intelligence
- Natural language processing
His scientific interests lie mostly in Artificial intelligence, Natural language processing, Linguistics, Speech recognition and Speech corpus.
His research in the fields of Named entity overlaps with other disciplines such as Induction method.
Mark Liberman combines subjects such as Annotation, Word, Information retrieval, Transcription and Applied linguistics with his study of Natural language processing.
His Linguistics research incorporates elements of Conversational speech and Parsing.
His research in Speech recognition tackles topics such as Mixture model which are related to areas like Cepstrum, Mel-frequency cepstrum, Range and Voice activity detection.
His Speech corpus study combines topics from a wide range of disciplines, such as Acoustic phonetics, Word recognition and Nonverbal communication.
His most cited work include:
- Procedure for quantitatively comparing the syntactic coverage of English grammars (421 citations)
- The intonational system of English (406 citations)
- UNIPEN project of on-line data exchange and recognizer benchmarks (376 citations)
What are the main themes of his work throughout his whole career to date?
Mark Liberman focuses on Speech recognition, Linguistics, Artificial intelligence, Natural language processing and Mandarin Chinese.
While the research belongs to areas of Speech recognition, he spends his time largely on the problem of Stress, intersecting his research to questions surrounding Intonation.
His work in Linguistics covers topics such as Annotation which are related to areas like Coreference.
His research in Artificial intelligence intersects with topics in Context, Software and Pattern recognition.
His Natural language processing research is multidisciplinary, incorporating elements of Speech corpus, Information retrieval and Phonetic transcription.
His research investigates the connection between Speaker diarisation and topics such as Robustness that intersect with issues in Voice activity detection.
He most often published in these fields:
- Speech recognition (33.52%)
- Linguistics (28.02%)
- Artificial intelligence (26.92%)
What were the highlights of his more recent work (between 2016-2021)?
- Speech recognition (33.52%)
- Audiology (6.04%)
- Linguistics (28.02%)
In recent papers he was focusing on the following fields of study:
Mark Liberman mostly deals with Speech recognition, Audiology, Linguistics, Speaker diarisation and Prosody.
Mark Liberman has included themes like Pronunciation, Segmentation and Word in his Speech recognition study.
The various areas that Mark Liberman examines in his Audiology study include Progressive supranuclear palsy, Atrophy and Cognitive impairment.
His study in American English and On Language falls under the purview of Linguistics.
His Speaker diarisation research focuses on Robustness and how it connects with Speech segmentation.
His Prosody research includes elements of Speech perception, Perception, Speech processing, Mode and Phonation.
Between 2016 and 2021, his most popular works were:
- The Second DIHARD Diarization Challenge: Dataset, Task, and Baselines. (53 citations)
- Linguistic camouflage in girls with autism spectrum disorder. (53 citations)
- Automatic measurement of prosody in behavioral variant FTD (22 citations)
In his most recent research, the most cited papers focused on:
- Linguistics
- Artificial intelligence
- Speech recognition
His primary areas of study are Speech recognition, Speaker diarisation, Robustness, Prosody and Speech segmentation.
His study ties his expertise on Segmentation together with the subject of Speech recognition.
He interconnects Duration, Selection, Standard Chinese, Agreement and Phone in the investigation of issues within Segmentation.
Mark Liberman conducts interdisciplinary study in the fields of Speaker diarisation and Speech enhancement through his research.
His study looks at the relationship between Prosody and topics such as Audiology, which overlap with Atrophy.
His Utterance study combines topics in areas such as Mode, Speech processing, Perception and TIMIT.
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.
