Yang Liu

What is he best known for?

The fields of study he is best known for:

• Artificial intelligence
• Machine learning
• Natural language processing

His scientific interests lie mostly in Artificial intelligence, Natural language processing, Speech recognition, Automatic summarization and Sentence. His study in the field of Sequence labeling also crosses realms of Cable television. Yang Liu mostly deals with Language model in his studies of Natural language processing.

When carried out as part of a general Speech recognition research project, his work on Hidden Markov model is frequently linked to work in Word recognition, therefore connecting diverse disciplines of study. His study in Hidden Markov model is interdisciplinary in nature, drawing from both Principle of maximum entropy, Word error rate, NIST and Conditional random field. He interconnects Text mining and Phrase in the investigation of issues within Automatic summarization.

His most cited work include:

• Automatic Summarization (357 citations)
• Enriching speech recognition with automatic detection of sentence boundaries and disfluencies (213 citations)
• Automatic dialog act segmentation and classification in multiparty meetings (169 citations)

What are the main themes of his work throughout his whole career to date?

The scientist’s investigation covers issues in Artificial intelligence, Natural language processing, Speech recognition, Sentence and Automatic summarization. His Artificial intelligence research includes themes of Machine learning and Pattern recognition. His research integrates issues of Normalization and Speech processing in his study of Natural language processing.

The concepts of his Speech recognition study are interwoven with issues in Feature extraction and Parsing. His study on Sentence also encompasses disciplines like

• Conditional random field, which have a strong connection to Sequence labeling,
• Metadata, which have a strong connection to Transcription. His research in Automatic summarization intersects with topics in Keyword extraction, Graph and Relevance.

He most often published in these fields:

• Artificial intelligence (77.08%)
• Natural language processing (60.42%)
• Speech recognition (58.85%)

What were the highlights of his more recent work (between 2016-2021)?

• Artificial intelligence (77.08%)
• Speech recognition (58.85%)
• Machine learning (17.71%)

In recent papers he was focusing on the following fields of study:

His primary areas of study are Artificial intelligence, Speech recognition, Machine learning, Context and Human–computer interaction. His Artificial intelligence research integrates issues from Social intelligence and Natural language processing. The concepts of his Natural language processing study are interwoven with issues in Ensemble systems and Training set.

His Speech recognition research incorporates elements of Pronunciation, Dialog system, Dialog box, Support vector machine and Minimal pair. His Machine learning research is multidisciplinary, relying on both Graph, Text mining, Domain knowledge, Argumentative and Machine translation. His Context research also works with subjects such as

• Style which is related to area like Parsing, Spoken language and Prosody,
• Sentence, which have a strong connection to Control, Hidden Markov model, Vowel and Dialog act.

Between 2016 and 2021, his most popular works were:

• A Multi-Task Learning Framework for Emotion Recognition Using 2D Continuous Space (97 citations)
• Using Context Information for Dialog Act Classification in DNN Framework (65 citations)
• An Ensemble Model Using Face and Body Tracking for Engagement Detection (21 citations)

In his most recent research, the most cited papers focused on:

• Artificial intelligence
• Machine learning
• Natural language processing

His main research concerns Speech recognition, Artificial intelligence, Artificial neural network, Dialog system and Machine learning. His research on Speech recognition focuses in particular on Speech synthesis. His Artificial intelligence study frequently links to other fields, such as Multi-task learning.

His studies in Artificial neural network integrate themes in fields like Feature engineering and Automated essay scoring, Natural language processing. His biological study spans a wide range of topics, including Motion, Speech analytics and Head. In general Machine learning study, his work on Test set and Ensemble forecasting often relates to the realm of Facial motion capture and Mean squared error, thereby connecting several areas of interest.