What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Daniel P. W. Ellis mainly investigates Speech recognition, Artificial intelligence, Pattern recognition, Audio signal processing and Hidden Markov model.
His Speech recognition study combines topics from a wide range of disciplines, such as Noise, Music theory and Mel-frequency cepstrum.
His research integrates issues of Natural language processing, Machine learning, Set and TRECVID in his study of Artificial intelligence.
His Pattern recognition research includes themes of Detector and Spectrogram.
His Audio signal processing research integrates issues from Music information retrieval, Algorithm design, Sequence, Variety and Sound recording and reproduction.
His Hidden Markov model research is multidisciplinary, incorporating perspectives in Artificial neural network, Transcription, Discriminative model and Chord.
His most cited work include:
- THE MILLION SONG DATASET (786 citations)
- Audio Set: An ontology and human-labeled dataset for audio events (699 citations)
- Tandem connectionist feature extraction for conventional HMM systems (687 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Speech recognition, Artificial intelligence, Pattern recognition, Audio signal processing and Natural language processing.
His research combines Feature extraction and Speech recognition.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Machine learning and Computer vision.
Acoustic model and Voice activity detection are the core of his Speech processing study.
He most often published in these fields:
- Speech recognition (60.25%)
- Artificial intelligence (40.00%)
- Pattern recognition (20.25%)
What were the highlights of his more recent work (between 2013-2021)?
- Speech recognition (60.25%)
- Artificial intelligence (40.00%)
- Pattern recognition (20.25%)
In recent papers he was focusing on the following fields of study:
His main research concerns Speech recognition, Artificial intelligence, Pattern recognition, Task and Event.
The Speech recognition study combines topics in areas such as Convolutional neural network and Sound.
His work deals with themes such as Machine learning and Natural language processing, which intersect with Artificial intelligence.
The various areas that Daniel P. W. Ellis examines in his Pattern recognition study include Event and Resolution.
His work in Task covers topics such as Vocabulary which are related to areas like Minimal supervision, Test set and Labeled data.
His Event research incorporates themes from Metadata, Feature extraction, Noise and Information retrieval.
Between 2013 and 2021, his most popular works were:
- Audio Set: An ontology and human-labeled dataset for audio events (699 citations)
- CNN architectures for large-scale audio classification (635 citations)
- librosa: Audio and Music Signal Analysis in Python (601 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Daniel P. W. Ellis focuses on Speech recognition, Artificial intelligence, Event, Information retrieval and Task.
Daniel P. W. Ellis has researched Speech recognition in several fields, including Sound, Deep learning, Vocabulary, Convolutional neural network and Speech Acoustics.
His Artificial intelligence study combines topics in areas such as Transcription, Natural language processing and Pattern recognition.
His Event research is multidisciplinary, incorporating elements of Feature extraction, Metadata and Noise.
His research in Information retrieval intersects with topics in Context, Field, Machine perception and Audio mining.
His Task research incorporates elements of Insect identification, Machine learning, Insect and Nearest neighbor search.
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.
