What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Machine learning
His scientific interests lie mostly in Speech recognition, Artificial intelligence, Pattern recognition, Hidden Markov model and Matrix decomposition.
His Speech recognition research incorporates themes from Audio signal processing, Harmonic, Speech enhancement, Polyphony and Convolutional neural network.
His work carried out in the field of Pattern recognition brings together such families of science as Recurrent neural network, Non-negative matrix factorization, Partial least squares regression and Spectrogram.
His work in Spectrogram addresses subjects such as Feature extraction, which are connected to disciplines such as Missing data.
In the field of Hidden Markov model, his study on Viterbi algorithm overlaps with subjects such as Acoustic event detection and In real life.
The Matrix decomposition study combines topics in areas such as Mel-frequency cepstrum and Blind signal separation.
His most cited work include:
- Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria (870 citations)
- Exemplar-Based Sparse Representations for Noise Robust Automatic Speech Recognition (323 citations)
- TUT database for acoustic scene classification and sound event detection (249 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Speech recognition, Pattern recognition, Spectrogram and Source separation.
The study incorporates disciplines such as Machine learning and Non-negative matrix factorization in addition to Artificial intelligence.
As a member of one scientific family, he mostly works in the field of Speech recognition, focusing on Artificial neural network and, on occasion, Intelligibility.
Tuomas Virtanen has researched Pattern recognition in several fields, including Sound event detection and Audio signal.
His Spectrogram research incorporates themes from Factorization and Deconvolution.
His Source separation research is multidisciplinary, incorporating elements of Audio signal processing and Signal.
He most often published in these fields:
- Artificial intelligence (55.02%)
- Speech recognition (51.78%)
- Pattern recognition (37.86%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (55.02%)
- Speech recognition (51.78%)
- Pattern recognition (37.86%)
In recent papers he was focusing on the following fields of study:
Tuomas Virtanen mainly focuses on Artificial intelligence, Speech recognition, Pattern recognition, Algorithm and Recurrent neural network.
Tuomas Virtanen combines subjects such as Machine learning and Natural language processing with his study of Artificial intelligence.
His Speech recognition study combines topics in areas such as Artificial neural network, Singing, Word and Convolutional neural network.
The concepts of his Pattern recognition study are interwoven with issues in Adversarial system, Annotation and Bilinear interpolation.
His research investigates the connection with Algorithm and areas like Non-negative matrix factorization which intersect with concerns in Matrix norm and Factorization.
His work deals with themes such as Feature extraction, Benchmark, Anechoic chamber and Word error rate, which intersect with Recurrent neural network.
Between 2017 and 2021, his most popular works were:
- Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge (132 citations)
- Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks (113 citations)
- A multi-device dataset for urban acoustic scene classification. (106 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Artificial intelligence, Pattern recognition, Speech recognition, Recurrent neural network and Spectrogram are his primary areas of study.
His studies in Artificial intelligence integrate themes in fields like Natural language processing, Machine learning and Audio signal.
His study looks at the intersection of Pattern recognition and topics like Adversarial system with Machine listening and Discriminative model.
His Speech recognition research is multidisciplinary, relying on both Singing and Convolutional neural network.
His Recurrent neural network research is multidisciplinary, incorporating perspectives in Feature extraction, Benchmark, Anechoic chamber and Word error rate.
His research in Spectrogram intersects with topics in Artificial neural network, Algorithm and Reverberation.
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.
