What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Speech recognition
- Programming language
Andreas Stolcke mainly investigates Artificial intelligence, Speech recognition, Natural language processing, Language model and Hidden Markov model.
His studies deal with areas such as Prosody and Pattern recognition as well as Artificial intelligence.
His Speech recognition research includes elements of Sentence, Sentence boundary disambiguation and Vocabulary.
His Natural language processing research includes themes of Segmentation, Dialog act, Conversation, Word and Transcription.
The concepts of his Language model study are interwoven with issues in Smoothing, Acoustic model, Decoding methods and Conversational speech.
The various areas that Andreas Stolcke examines in his Hidden Markov model study include Decision tree and Hidden semi-Markov model, Causal Markov condition, Markov property.
His most cited work include:
- SRILM – An Extensible Language Modeling Toolkit (3943 citations)
- Dialogue act modeling for automatic tagging and recognition of conversational speech (847 citations)
- Finding consensus in speech recognition: word error minimization and other applications of confusion networks☆ (710 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Speech recognition, Artificial intelligence, Natural language processing, Language model and Word error rate.
His research related to NIST, Speaker recognition, Speaker diarisation, Hidden Markov model and Acoustic model might be considered part of Speech recognition.
His Artificial intelligence research incorporates elements of Prosody, Vocabulary and Pattern recognition.
While the research belongs to areas of Natural language processing, Andreas Stolcke spends his time largely on the problem of Speech technology, intersecting his research to questions surrounding Speech analytics.
His work on Perplexity is typically connected to Cache language model as part of general Language model study, connecting several disciplines of science.
The study incorporates disciplines such as Transcription, Decoding methods, Reduction and Test set in addition to Word error rate.
He most often published in these fields:
- Speech recognition (79.93%)
- Artificial intelligence (63.08%)
- Natural language processing (41.58%)
What were the highlights of his more recent work (between 2014-2021)?
- Speech recognition (79.93%)
- Artificial intelligence (63.08%)
- Natural language processing (41.58%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Speech recognition, Artificial intelligence, Natural language processing, Word error rate and Language model.
Andreas Stolcke has included themes like End-to-end principle and Test set in his Speech recognition study.
Artificial intelligence is frequently linked to Pattern recognition in his study.
Andreas Stolcke combines subjects such as Visualization, Feature extraction, Word and Pseudoword with his study of Natural language processing.
His Word error rate study integrates concerns from other disciplines, such as Acoustic model, Dialog box and Reduction.
His Language model research is multidisciplinary, relying on both Machine learning, Recurrent neural network, Utterance and Benchmark.
Between 2014 and 2021, his most popular works were:
- Achieving Human Parity in Conversational Speech Recognition (348 citations)
- The Microsoft 2017 Conversational Speech Recognition System (228 citations)
- The microsoft 2016 conversational speech recognition system (221 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Speech recognition
Andreas Stolcke focuses on Speech recognition, Language model, Word error rate, NIST and Artificial intelligence.
His research in Speech recognition intersects with topics in Time delay neural network and Test set.
His biological study spans a wide range of topics, including Information extraction, Recurrent neural network and Utterance.
Andreas Stolcke interconnects Acoustic model and Dialog box in the investigation of issues within Word error rate.
His work carried out in the field of Artificial intelligence brings together such families of science as Pattern recognition, Human–computer interaction and Natural language processing.
Andreas Stolcke has researched Natural language processing in several fields, including Visualization, Feature extraction, Expression and Modality.
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.
