What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Artificial neural network
Nima Mesgarani mainly focuses on Speech recognition, Auditory cortex, Speech processing, Neurocomputational speech processing and Spectrogram.
His research investigates the connection between Speech recognition and topics such as Speech perception that intersect with problems in Cocktail party effect.
His Auditory cortex research is multidisciplinary, incorporating elements of Acoustics, Natural sounds, Receptive field, Stimulus and Speech Acoustics.
His biological study spans a wide range of topics, including Phonetics and Perception.
In his work, Time–frequency analysis is strongly intertwined with Source separation, which is a subfield of Speech processing.
His research investigates the link between Neurocomputational speech processing and topics such as Syllable that cross with problems in Brain activity and meditation, Cerebral cortex, Functional organization, Speech production and Sensorimotor cortex.
His most cited work include:
- Selective cortical representation of attended speaker in multi-talker speech perception (551 citations)
- Phonetic feature encoding in human superior temporal gyrus (531 citations)
- Reconstructing Speech from Human Auditory Cortex (413 citations)
What are the main themes of his work throughout his whole career to date?
Speech recognition, Auditory cortex, Artificial intelligence, Speech processing and Deep learning are his primary areas of study.
He combines subjects such as Artificial neural network and Speech perception, Neurocomputational speech processing with his study of Speech recognition.
His work deals with themes such as Syllable and Speech Acoustics, which intersect with Neurocomputational speech processing.
Nima Mesgarani has included themes like Stimulus, Neurophysiology, Receptive field and Perception in his Auditory cortex study.
His work on Attractor network and Robustness is typically connected to Node as part of general Artificial intelligence study, connecting several disciplines of science.
His studies in Deep learning integrate themes in fields like Embedding, Algorithm, Source separation and Time–frequency analysis.
He most often published in these fields:
- Speech recognition (62.77%)
- Auditory cortex (32.12%)
- Artificial intelligence (26.28%)
What were the highlights of his more recent work (between 2019-2021)?
- Speech recognition (62.77%)
- Separation (8.76%)
- Auditory cortex (32.12%)
In recent papers he was focusing on the following fields of study:
Speech recognition, Separation, Auditory cortex, Artificial intelligence and Neuroscience are his primary areas of study.
His work on Intelligibility as part of general Speech recognition research is often related to Hierarchy, thus linking different fields of science.
The various areas that Nima Mesgarani examines in his Auditory cortex study include Neurophysiology, Normalization, Gyrus, Speech processing and Stimulus.
As part of one scientific family, Nima Mesgarani deals mainly with the area of Normalization, narrowing it down to issues related to the Tonotopy, and often Feature and Speech perception.
The study incorporates disciplines such as Neural correlates of consciousness, Planum temporale and Brain activity and meditation in addition to Gyrus.
His studies examine the connections between Artificial intelligence and genetics, as well as such issues in Pattern recognition, with regards to Visual word recognition, Representation and Biological neural network.
Between 2019 and 2021, his most popular works were:
- End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation (28 citations)
- Cortical Encoding of Melodic Expectations in Human Temporal Cortex (9 citations)
- Separating Varying Numbers of Sources with Auxiliary Autoencoding Loss (7 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Speech recognition
- Artificial neural network
Nima Mesgarani mainly focuses on Artificial intelligence, Algorithm, End-to-end principle, Deep learning and Speech recognition.
His Artificial intelligence research includes themes of Microphone array and Beamforming.
In general Algorithm, his work in Source separation is often linked to Stopping time, Invariant and Fault tolerance linking many areas of study.
His Deep learning study combines topics in areas such as Intelligibility, High fidelity, Binaural recording and Sound localization.
In his research, Stimulus, Sensory system and Auditory cortex is intimately related to Receptive field, which falls under the overarching field of Artificial neural network.
His Auditory cortex study results in a more complete grasp of Neuroscience.
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.
