What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
His primary scientific interests are in Speech recognition, Language model, Artificial intelligence, Word error rate and Artificial neural network. His work deals with themes such as Time delay neural network and Deep neural networks, which intersect with Speech recognition. His study in Language model is interdisciplinary in nature, drawing from both Natural language and Hidden Markov model.
His Artificial intelligence study combines topics in areas such as Machine learning and Natural language processing. His studies deal with areas such as Contrast and Adaptation as well as Natural language processing. His Word error rate research integrates issues from Word, Dictation and Voice search.
His most cited work include:
- State-of-the-Art Speech Recognition with Sequence-to-Sequence Models (471 citations)
- Unsupervised language model adaptation (142 citations)
- Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home (137 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, Artificial neural network, Acoustic model and Natural language processing. His work in the fields of Speech recognition, such as Language model and Word error rate, overlaps with other areas such as Vocabulary and Pronunciation. His Language model research is multidisciplinary, incorporating elements of Natural language and Voice search.
His Artificial intelligence study integrates concerns from other disciplines, such as Estimation theory, Machine learning, Adaptation and Pattern recognition. As a part of the same scientific study, Michiel Bacchiani usually deals with the Artificial neural network, concentrating on Speech enhancement and frequently concerns with Speech processing. His Acoustic model study combines topics from a wide range of disciplines, such as Speaker recognition, Training set and Hidden Markov model.
He most often published in these fields:
- Speech recognition (62.35%)
- Artificial intelligence (38.82%)
- Artificial neural network (16.47%)
What were the highlights of his more recent work (between 2016-2020)?
- Speech recognition (62.35%)
- Artificial neural network (16.47%)
- Word error rate (14.12%)
In recent papers he was focusing on the following fields of study:
Michiel Bacchiani focuses on Speech recognition, Artificial neural network, Word error rate, Word and Artificial intelligence. His work on Encoder expands to the thematically related Speech recognition. Michiel Bacchiani interconnects Algorithm, Voice activity detection and Speech coding in the investigation of issues within Artificial neural network.
His research investigates the connection between Word error rate and topics such as Beamforming that intersect with issues in Speech enhancement. His Artificial intelligence research includes elements of Domain and Pattern recognition. His Dictation study combines topics in areas such as Language model, Hidden Markov model and Task.
Between 2016 and 2020, his most popular works were:
- State-of-the-Art Speech Recognition with Sequence-to-Sequence Models (471 citations)
- Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home (137 citations)
- Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition (118 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
His primary areas of study are Speech recognition, Word error rate, Pronunciation, Artificial intelligence and Sequence. His Speech recognition research integrates issues from Data modeling and Deep neural networks. His work in Pronunciation incorporates the disciplines of Language model, Word, Dictation and Voice search.
Michiel Bacchiani has researched Language model in several fields, including Encoder, Task and Hidden Markov model. His Artificial intelligence research is multidisciplinary, relying on both Domain and Implementation. His work deals with themes such as Artificial neural network and Representation, which intersect with Sequence.
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.
