What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
His main research concerns Speech recognition, Artificial intelligence, Valence, Emotion classification and Natural language processing.
He integrates several fields in his works, including Speech recognition and Emotion perception.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Metadata, Music information retrieval, Machine learning, Melody and Pattern recognition.
His Valence research focuses on Categorical variable and how it connects with Support vector machine and Regression analysis.
His Emotion classification research is multidisciplinary, relying on both Variation, Feeling, Class and Fuzzy logic.
In his study, which falls under the umbrella issue of Natural language processing, Timbre and Musical is strongly linked to Arousal.
His most cited work include:
- A Regression Approach to Music Emotion Recognition (315 citations)
- Machine Recognition of Music Emotion: A Review (237 citations)
- Music emotion classification: a fuzzy approach (125 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Speech recognition, Machine learning, Music information retrieval and Natural language processing.
The various areas that he examines in his Artificial intelligence study include Context and Pattern recognition.
His Spectrogram study in the realm of Speech recognition interacts with subjects such as Emotion perception.
His work in the fields of Machine learning, such as Recommender system, Feature learning and Support vector machine, intersects with other areas such as TRECVID.
Within one scientific family, Yi-Hsuan Yang focuses on topics pertaining to Multimedia under Music information retrieval, and may sometimes address concerns connected to Pop music automation.
His studies examine the connections between Natural language processing and genetics, as well as such issues in Set, with regards to Feature.
He most often published in these fields:
- Artificial intelligence (45.45%)
- Speech recognition (42.42%)
- Machine learning (19.05%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (45.45%)
- Speech recognition (42.42%)
- Machine learning (19.05%)
In recent papers he was focusing on the following fields of study:
Yi-Hsuan Yang mainly focuses on Artificial intelligence, Speech recognition, Machine learning, Musical and Deep learning.
His work often combines Artificial intelligence and MIDI studies.
His Speech recognition research incorporates themes from Generative grammar and Set.
His Machine learning research is multidisciplinary, incorporating perspectives in Embedding, Source separation, Generative model and Jazz.
Yi-Hsuan Yang interconnects Web application, Interactivity and Rendering in the investigation of issues within Musical.
His studies in Deep learning integrate themes in fields like Musical composition, Music information retrieval and Natural language processing.
Between 2018 and 2021, his most popular works were:
- Collaborative Similarity Embedding for Recommender Systems (26 citations)
- Dilated Convolution with Dilated GRU for Music Source Separation. (22 citations)
- Learning to Match Transient Sound Events Using Attentional Similarity for Few-shot Sound Recognition (21 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
Yi-Hsuan Yang focuses on Artificial intelligence, Speech recognition, Musical, Task analysis and Polyphony.
His Artificial intelligence study integrates concerns from other disciplines, such as Frame and Machine learning.
He has researched Machine learning in several fields, including Embedding, Graph and Bipartite graph, Graph.
His Speech recognition study frequently draws parallels with other fields, such as Feature extraction.
His work deals with themes such as Pipeline, Generative grammar, Inference and Speech synthesis, which intersect with Musical.
Yi-Hsuan Yang has included themes like Code, Composition and Natural language processing in his Timbre study.
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.
