What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Linguistics
Speech recognition, Artificial intelligence, Speech processing, Natural language processing and Pattern recognition are his primary areas of study.
His Speech recognition study frequently links to related topics such as Valence.
In his study, Speech production is inextricably linked to Computer vision, which falls within the broad field of Artificial intelligence.
Shrikanth S. Narayanan usually deals with Speech processing and limits it to topics linked to Audio signal processing and Abstraction.
His Natural language processing research incorporates elements of Speech corpus and Spoken dialog systems.
His Pattern recognition study combines topics in areas such as Time domain and Bayesian probability.
His most cited work include:
- IEMOCAP: interactive emotional dyadic motion capture database (895 citations)
- Toward detecting emotions in spoken dialogs (731 citations)
- Analysis of emotion recognition using facial expressions, speech and multimodal information (617 citations)
What are the main themes of his work throughout his whole career to date?
Shrikanth S. Narayanan spends much of his time researching Speech recognition, Artificial intelligence, Natural language processing, Pattern recognition and Vocal tract.
Speech processing, Speech production, Hidden Markov model, Word error rate and Speaker recognition are among the areas of Speech recognition where the researcher is concentrating his efforts.
Shrikanth S. Narayanan does research in Artificial intelligence, focusing on Feature extraction specifically.
His study in Natural language processing is interdisciplinary in nature, drawing from both Speech corpus and Prosody.
His work carried out in the field of Vocal tract brings together such families of science as Tongue, Articulation and Real-time MRI.
He most often published in these fields:
- Speech recognition (50.31%)
- Artificial intelligence (42.65%)
- Natural language processing (17.36%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (42.65%)
- Speech recognition (50.31%)
- Task (6.41%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Speech recognition, Task, Natural language processing and Speaker diarisation.
The study incorporates disciplines such as Context, Machine learning and Pattern recognition in addition to Artificial intelligence.
His Speech recognition research integrates issues from Embedding and Robustness.
The Task study combines topics in areas such as Human behavior and Spoken language.
His Natural language processing research is multidisciplinary, incorporating elements of Annotation and Word.
His Speaker diarisation research is multidisciplinary, incorporating perspectives in Encoder and Cluster analysis.
Between 2017 and 2021, his most popular works were:
- NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning. (33 citations)
- Irregularity-Aware Graph Fourier Transforms (32 citations)
- A Computational Study of Expressive Facial Dynamics in Children with Autism (28 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Linguistics
- Statistics
His main research concerns Speech recognition, Artificial intelligence, Task, Wearable computer and Speaker diarisation.
His work deals with themes such as Embedding and Cluster analysis, which intersect with Speech recognition.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Context, Machine learning, Pattern recognition and Natural language processing.
His work is dedicated to discovering how Natural language processing, Word are connected with Emotion classification and other disciplines.
His research in Wearable computer intersects with topics in Big Five personality traits, Applied psychology, Data set and Set.
He interconnects Transcription, Encoder and Spectral clustering in the investigation of issues within Speaker diarisation.
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.
