What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Beamforming, Word error rate and Speech enhancement.
His research in Speech recognition intersects with topics in Artificial neural network and Signal processing.
The study incorporates disciplines such as Pattern recognition and Natural language processing in addition to Artificial intelligence.
His Beamforming research incorporates themes from Acoustic model, Source separation and Expectation–maximization algorithm.
His Speech enhancement study incorporates themes from Reverberation, Blind signal separation, Speech processing, Microphone and Algorithm.
Reinhold Haeb-Umbach has researched Speech processing in several fields, including Time delay neural network and Noise.
His most cited work include:
- Multiclass linear dimension reduction by weighted pairwise Fisher criteria (425 citations)
- An overview of noise-robust automatic speech recognition (334 citations)
- Linear discriminant analysis for improved large vocabulary continuous speech recognition (292 citations)
What are the main themes of his work throughout his whole career to date?
Reinhold Haeb-Umbach focuses on Speech recognition, Artificial intelligence, Pattern recognition, Algorithm and Speech enhancement.
The various areas that Reinhold Haeb-Umbach examines in his Speech recognition study include Artificial neural network, Beamforming and Noise.
Many of his studies on Artificial intelligence involve topics that are commonly interrelated, such as Natural language processing.
The Pattern recognition study combines topics in areas such as Bayesian probability and Cluster analysis.
His study in Algorithm is interdisciplinary in nature, drawing from both Frequency domain and Filter.
His Speech enhancement research incorporates themes from Noise reduction and Reverberation.
He most often published in these fields:
- Speech recognition (56.27%)
- Artificial intelligence (36.61%)
- Pattern recognition (22.37%)
What were the highlights of his more recent work (between 2017-2021)?
- Speech recognition (56.27%)
- Artificial neural network (13.90%)
- Source separation (7.80%)
In recent papers he was focusing on the following fields of study:
Reinhold Haeb-Umbach mostly deals with Speech recognition, Artificial neural network, Source separation, Artificial intelligence and Beamforming.
Reinhold Haeb-Umbach is interested in Word error rate, which is a field of Speech recognition.
His Artificial neural network research is multidisciplinary, incorporating perspectives in Smoothing, Contrast, Spectral density, Estimator and Mixture model.
His Source separation study integrates concerns from other disciplines, such as Randomness, Word, Speaker diarisation and Blind signal separation.
His research investigates the connection with Artificial intelligence and areas like Pattern recognition which intersect with concerns in Inference.
His work in Beamforming tackles topics such as Noise which are related to areas like Compensation and Covariance matrix.
Between 2017 and 2021, his most popular works were:
- NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing (50 citations)
- Front-end processing for the CHiME-5 dinner party scenario (44 citations)
- Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition (41 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His primary areas of study are Speech recognition, Artificial neural network, Source separation, Word error rate and Artificial intelligence.
His Speech recognition study incorporates themes from Speech enhancement and Reverberation.
His research integrates issues of Estimator and Beamforming in his study of Artificial neural network.
The concepts of his Word error rate study are interwoven with issues in Reduction and Joint.
His Artificial intelligence study frequently draws connections to adjacent fields such as Pattern recognition.
In the field of Pattern recognition, his study on Hidden Markov model overlaps with subjects such as Initialization.
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.
