What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Hsin-Min Wang mainly focuses on Speech recognition, Artificial intelligence, Natural language processing, Mandarin Chinese and Syllable.
His study in Speech recognition is interdisciplinary in nature, drawing from both Mixture model, Vocabulary and Generative model.
His studies in Artificial intelligence integrate themes in fields like Decoding methods, Cable television and Pattern recognition.
His studies deal with areas such as Document retrieval, Search engine indexing and Hidden Markov model as well as Natural language processing.
Hsin-Min Wang interconnects The Internet, Natural language and Speech processing in the investigation of issues within Mandarin Chinese.
His Syllable study incorporates themes from Speech corpus and Chinese language.
His most cited work include:
- A DISTRIBUTED ARCHITECTURE FOR COOPERATIVE SPOKEN DIALOGUE AGENTS WITH COHERENT DIALOGUE STATE AND HISTORY (237 citations)
- Golden Mandarin(II)-an intelligent Mandarin dictation machine for Chinese character input with adaptation/learning functions (161 citations)
- Voice conversion from non-parallel corpora using variational auto-encoder (139 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Speech recognition, Natural language processing, Pattern recognition and Mandarin Chinese.
His work in Artificial intelligence tackles topics such as Machine learning which are related to areas like Training set.
The concepts of his Speech recognition study are interwoven with issues in Speech enhancement and Vocabulary.
The Natural language processing study combines topics in areas such as Context and Information retrieval, Relevance, Search engine indexing.
His study looks at the relationship between Pattern recognition and topics such as Cluster analysis, which overlap with Bayesian information criterion.
His Syllable research incorporates elements of Natural language and Chinese language.
He most often published in these fields:
- Artificial intelligence (62.08%)
- Speech recognition (55.90%)
- Natural language processing (31.46%)
What were the highlights of his more recent work (between 2018-2021)?
- Speech recognition (55.90%)
- Artificial intelligence (62.08%)
- Speech enhancement (11.24%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Speech recognition, Artificial intelligence, Speech enhancement, Deep learning and Autoencoder.
His Speech recognition research is mostly focused on the topic Language model.
Hsin-Min Wang interconnects Acoustic model and Mandarin Chinese in the investigation of issues within Language model.
In the field of Artificial intelligence, his study on Training set overlaps with subjects such as Naturalness.
His Speech enhancement research is multidisciplinary, relying on both Intelligibility, Noise measurement, Noise reduction and Audio visual.
In his research, Classifier and Similarity is intimately related to Code, which falls under the overarching field of Autoencoder.
Between 2018 and 2021, his most popular works were:
- ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (25 citations)
- MOSNet: Deep Learning-Based Objective Assessment for Voice Conversion. (24 citations)
- Refined WaveNet Vocoder for Variational Autoencoder Based Voice Conversion (17 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His scientific interests lie mostly in Speech recognition, Artificial intelligence, Speech enhancement, Deep learning and Autoencoder.
As a member of one scientific family, Hsin-Min Wang mostly works in the field of Speech recognition, focusing on Artificial neural network and, on occasion, Signal-to-noise ratio, Reinforcement learning, Language model, Word error rate and Mandarin Chinese.
His work in the fields of Artificial intelligence, such as Generative model, overlaps with other areas such as Naturalness.
His work carried out in the field of Speech enhancement brings together such families of science as Encoder, Noise reduction and Model selection.
His Autoencoder research is multidisciplinary, incorporating elements of Transfer of learning, Code and Classifier, Pattern recognition.
In the field of Pattern recognition, his study on Training set overlaps with subjects such as Similarity, Test data, Structure and Frame.
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.
