What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
Karen Livescu mainly investigates Artificial intelligence, Speech recognition, Pattern recognition, Natural language processing and Word.
Her study explores the link between Artificial intelligence and topics such as Machine learning that cross with problems in Variety.
Her Speech recognition research is multidisciplinary, relying on both Artificial neural network, Embedding, Dynamic Bayesian network and Training set.
The study incorporates disciplines such as Correlation clustering, Determining the number of clusters in a data set and Single-linkage clustering in addition to Pattern recognition.
In her study, which falls under the umbrella issue of Natural language processing, Named-entity recognition, Context, Phrase, Semantic resource and Leverage is strongly linked to Bigram.
Her work carried out in the field of Word brings together such families of science as Sentence, Similarity, Task and Parsing.
Her most cited work include:
- Deep Canonical Correlation Analysis (943 citations)
- Multi-view clustering via canonical correlation analysis (536 citations)
- On Deep Multi-View Representation Learning (379 citations)
What are the main themes of her work throughout her whole career to date?
Karen Livescu spends much of her time researching Speech recognition, Artificial intelligence, Natural language processing, Word and Pattern recognition.
Her Speech recognition study incorporates themes from Pronunciation, Feature, Dynamic Bayesian network, Discriminative model and Fingerspelling.
Her research integrates issues of Context, Machine learning and Task in her study of Artificial intelligence.
Her Natural language processing study combines topics from a wide range of disciplines, such as Variation, Data set and Phone.
Her research in Word intersects with topics in Dynamic time warping, Recurrent neural network, Margin, Embedding and Vocabulary.
Her work deals with themes such as Singular value decomposition, Feature learning and Kernel, which intersect with Canonical correlation.
She most often published in these fields:
- Speech recognition (59.88%)
- Artificial intelligence (59.30%)
- Natural language processing (30.81%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (59.30%)
- Natural language processing (30.81%)
- Task (13.37%)
In recent papers she was focusing on the following fields of study:
Artificial intelligence, Natural language processing, Task, Speech recognition and Word are her primary areas of study.
Her research investigates the connection with Artificial intelligence and areas like Machine learning which intersect with concerns in Generative model.
Many of her research projects under Natural language processing are closely connected to Matching with Matching, tying the diverse disciplines of science together.
Her biological study deals with issues like Language model, which deal with fields such as State and Notation.
Her Speech recognition study integrates concerns from other disciplines, such as Sign language, American Sign Language, Fingerspelling and Vocabulary.
Her work on Sequence labeling as part of general Word study is frequently connected to Set and Term, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
Between 2018 and 2021, her most popular works were:
- Pre-training on high-resource speech recognition improves low-resource speech-to-text translation (61 citations)
- Visually Grounded Neural Syntax Acquisition (32 citations)
- Unsupervised Pre-Training of Bidirectional Speech Encoders via Masked Reconstruction (28 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Karen Livescu mostly deals with Artificial intelligence, Natural language processing, Speech recognition, Task and Encoder.
Many of her studies on Artificial intelligence apply to Constructed language as well.
Her studies deal with areas such as Task analysis, Data set and Coreference as well as Natural language processing.
Her Speech recognition research is multidisciplinary, incorporating elements of Vocabulary and Word embedding.
The various areas that she examines in her Task study include Embedding and Function.
Karen Livescu combines subjects such as Context, Segmentation, Speech processing, External image and Semantics with her study of Visualization.
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.
