Lalit R. Bahl

What is he best known for?

The fields of study he is best known for:

• Artificial intelligence
• Speech recognition
• Algorithm

Lalit R. Bahl spends much of his time researching Speech recognition, Artificial intelligence, Markov model, Natural language processing and Word. The various areas that Lalit R. Bahl examines in his Speech recognition study include Natural language, Statistical model and Feature vector. His Maximum-entropy Markov model study in the realm of Markov model interacts with subjects such as Sequence and Pronunciation.

His Language model study, which is part of a larger body of work in Natural language processing, is frequently linked to Alphabet, Simple and Phone, bridging the gap between disciplines. His study explores the link between Word and topics such as Binary decision diagram that cross with problems in Node and Binary tree. As a part of the same scientific study, Lalit R. Bahl usually deals with the Speech processing, concentrating on Estimation theory and frequently concerns with Expectation–maximization algorithm and Hidden semi-Markov model.

His most cited work include:

• Optimal decoding of linear codes for minimizing symbol error rate (Corresp.) (4485 citations)
• A Maximum Likelihood Approach to Continuous Speech Recognition (1381 citations)
• Maximum mutual information estimation of hidden Markov model parameters for speech recognition (745 citations)

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

His scientific interests lie mostly in Speech recognition, Artificial intelligence, Word, Natural language processing and Markov model. His research brings together the fields of Natural language and Speech recognition. His work deals with themes such as Value, Set and Pattern recognition, which intersect with Artificial intelligence.

Lalit R. Bahl focuses mostly in the field of Word, narrowing it down to matters related to String and, in some cases, Speech input. His Natural language processing study combines topics from a wide range of disciplines, such as Tree and Speech synthesis. His Markov model research is multidisciplinary, incorporating elements of Substring and Component.

He most often published in these fields:

• Speech recognition (72.61%)
• Artificial intelligence (54.78%)
• Word (33.12%)

What were the highlights of his more recent work (between 1994-1999)?

• Speech recognition (72.61%)
• Artificial intelligence (54.78%)
• Pattern recognition (21.66%)

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

His main research concerns Speech recognition, Artificial intelligence, Pattern recognition, Natural language processing and Speaker recognition. His Speech recognition study typically links adjacent topics like Word. His Decision tree study in the realm of Artificial intelligence connects with subjects such as Transcription.

His work in the fields of Pattern recognition, such as Feature vector and Mutual information, overlaps with other areas such as Gaussian process. The Natural language research he does as part of his general Natural language processing study is frequently linked to other disciplines of science, such as Specific model, therefore creating a link between diverse domains of science. His studies deal with areas such as Feature extraction and Training set as well as Speech processing.

Between 1994 and 1999, his most popular works were:

• Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task (233 citations)
• Experiments using data augmentation for speaker adaptation (161 citations)
• Speaker clustering and transformation for speaker adaptation in speech recognition systems (86 citations)

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

• Artificial intelligence
• Programming language
• Algorithm

Lalit R. Bahl mainly focuses on Speech recognition, Artificial intelligence, Natural language processing, Speaker recognition and Speaker diarisation. Lalit R. Bahl is involved in the study of Speech recognition that focuses on Speech processing in particular. When carried out as part of a general Artificial intelligence research project, his work on Decision tree and Feature vector is frequently linked to work in Hierarchical database model, therefore connecting diverse disciplines of study.

In the subject of general Natural language processing, his work in Natural language is often linked to Pronunciation and Space, thereby combining diverse domains of study. His Natural language research integrates issues from Speech corpus and Word. His Speaker recognition research includes elements of Cluster analysis and Word error rate.