What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
His primary areas of study are Artificial intelligence, Speech recognition, Natural language processing, Speaker recognition and Pattern recognition.
His Artificial intelligence study frequently links to adjacent areas such as Computer vision.
Speech recognition and Normalization are commonly linked in his work.
His study on Natural language processing is mostly dedicated to connecting different topics, such as Word.
His research in Speaker recognition intersects with topics in Speech synthesis, Covariance, Spoofing attack and Voice activity detection.
His work deals with themes such as Spike train, Signal processing, Robustness and Spectrogram, which intersect with Pattern recognition.
His most cited work include:
- An overview of text-independent speaker recognition: From features to supervectors (1045 citations)
- Spoofing and countermeasures for speaker verification (280 citations)
- A Joint Source-Channel Model for Machine Transliteration (237 citations)
What are the main themes of his work throughout his whole career to date?
Haizhou Li mainly investigates Speech recognition, Artificial intelligence, Natural language processing, Pattern recognition and NIST.
His work in Speech recognition is not limited to one particular discipline; it also encompasses Feature extraction.
His Artificial intelligence study frequently draws parallels with other fields, such as Machine learning.
His research links Task with Natural language processing.
His Pattern recognition research incorporates elements of Feature and Spiking neural network.
NIST is frequently linked to Discriminative model in his study.
He most often published in these fields:
- Speech recognition (61.48%)
- Artificial intelligence (58.57%)
- Natural language processing (24.30%)
What were the highlights of his more recent work (between 2017-2021)?
- Speech recognition (61.48%)
- Artificial intelligence (58.57%)
- Artificial neural network (9.63%)
In recent papers he was focusing on the following fields of study:
Haizhou Li mainly focuses on Speech recognition, Artificial intelligence, Artificial neural network, Spiking neural network and Prosody.
His Speech recognition research includes themes of Embedding, Singing and Feature extraction.
The study incorporates disciplines such as Natural language processing, Machine learning and Pattern recognition in addition to Artificial intelligence.
His work in Spiking neural network addresses subjects such as Backpropagation, which are connected to disciplines such as Spike.
The Prosody study combines topics in areas such as Identity, Identity, State and Speech synthesis.
His work focuses on many connections between Speaker verification and other disciplines, such as Spoofing attack, that overlap with his field of interest in Replay attack and Convolutional neural network.
Between 2017 and 2021, his most popular works were:
- Unsupervised Domain Adaptation via Domain Adversarial Training for Speaker Recognition (60 citations)
- A Cost-Sensitive Deep Belief Network for Imbalanced Classification (59 citations)
- A Voice Conversion Framework with Tandem Feature Sparse Representation and Speaker-Adapted WaveNet Vocoder. (53 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His main research concerns Speech recognition, Artificial intelligence, Spiking neural network, Prosody and Artificial neural network.
His Speech recognition study combines topics in areas such as Embedding, Feature extraction and Identity.
His Artificial intelligence research incorporates elements of Machine learning, Spoofing attack and Pattern recognition.
His study looks at the relationship between Pattern recognition and fields such as MNIST database, as well as how they intersect with chemical problems.
His Spiking neural network research is multidisciplinary, incorporating elements of Event, Neuromorphic engineering, Filter bank and Learning rule.
His Deep learning study incorporates themes from Speech enhancement and Utterance.
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.
