What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Artificial intelligence, Machine learning, Speech recognition, Rhythm and Multimedia.
His Artificial intelligence research focuses on Noise in particular.
His study in the fields of Unsupervised learning, Learning classifier system and Instance-based learning under the domain of Machine learning overlaps with other disciplines such as MOZART.
His Speech recognition study incorporates themes from Classifier, False positive paradox and Musical.
The Rhythm study combines topics in areas such as Timbre, Beat, Audio analyzer and Metaphor.
His Multimedia research includes elements of Metadata, Heuristics and Human–computer interaction.
His most cited work include:
- Learning in the presence of concept drift and hidden contexts (1330 citations)
- Incremental reduced error pruning (308 citations)
- Improvements of Audio-Based Music Similarity and Genre Classificaton. (206 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, Musical and Piano.
His research investigates the connection with Artificial intelligence and areas like Pattern recognition which intersect with concerns in Audio signal.
His Speech recognition study integrates concerns from other disciplines, such as Identification, Chord, Score following, Beat and Polyphony.
His works in Recurrent neural network and Unsupervised learning are all subjects of inquiry into Machine learning.
Gerhard Widmer studies Musical, namely Music information retrieval.
His research ties Dynamics and Piano together.
He most often published in these fields:
- Artificial intelligence (48.33%)
- Speech recognition (26.74%)
- Machine learning (17.48%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (48.33%)
- Speech recognition (26.74%)
- Natural language processing (11.83%)
In recent papers he was focusing on the following fields of study:
Gerhard Widmer mostly deals with Artificial intelligence, Speech recognition, Natural language processing, Convolutional neural network and Chord.
His research integrates issues of Machine learning, Score following and Pattern recognition in his study of Artificial intelligence.
He works mostly in the field of Speech recognition, limiting it down to concerns involving Polyphony and, occasionally, Voice leading and Cadence.
His research in Natural language processing intersects with topics in Harmony, Perception, Musical and Piano.
His Convolutional neural network research is multidisciplinary, incorporating perspectives in Transcription, Generalization and Margin.
His Chord research incorporates elements of Language model, Recurrent neural network, Autoencoder, Mean reciprocal rank and String.
Between 2017 and 2021, his most popular works were:
- Learning Audio–Sheet Music Correspondences for Cross-Modal Retrieval and Piece Identification (28 citations)
- End-to-end cross-modality retrieval with CCA projections and pairwise ranking loss (26 citations)
- End-to-end cross-modality retrieval with CCA projections and pairwise ranking loss (26 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Gerhard Widmer spends much of his time researching Information retrieval, Artificial intelligence, Recommender system, Speech recognition and Modality.
His study looks at the relationship between Information retrieval and fields such as Key, as well as how they intersect with chemical problems.
His Artificial intelligence research integrates issues from Computational musicology and Natural language processing.
His work deals with themes such as Context, Music information retrieval and Feature vector, which intersect with Recommender system.
His studies in Speech recognition integrate themes in fields like Chord, Recurrent neural network and Melody.
His studies examine the connections between Modality and genetics, as well as such issues in Contrast, with regards to Artificial neural network.
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.
