A
A. G. Ramakrishnan
Researcher at Indian Institute of Science
Publications - 228
Citations - 3486
A. G. Ramakrishnan is an academic researcher from Indian Institute of Science. The author has contributed to research in topics: Handwriting recognition & Wavelet transform. The author has an hindex of 28, co-authored 220 publications receiving 3111 citations. Previous affiliations of A. G. Ramakrishnan include Birla Institute of Technology and Science.
Papers
More filters
Journal ArticleDOI
Cumulative Impulse Strength for Epoch Extraction
TL;DR: A temporal measure termed the cumulative impulse strength is proposed for locating the impulses in a quasi-periodic impulse-sequence embedded in noise and applied for detecting the GCIs from the inverted integrated LPR using a recursive algorithm.
Proceedings Article
Automatic Generation of Compound Word Lexicon for Hindi Speech Synthesis
TL;DR: This paper proposes a new technique for automatic extraction of compound words from Hindi corpus and shows an improvement of 1.6% in Hindi Grapheme-to-Phoneme (G2P) conversion as a result of using a phonetized compound word lexicon, created by the above technique.
Journal ArticleDOI
Estimation of voice-onset time in continuous speech using temporal measures
TL;DR: An automatic acoustic-phonetic method for estimating voice-onset time of stops that makes use of the plosion index for the automatic detection of burst onsets of stops and compares well with three state-of-the-art techniques.
Journal ArticleDOI
Bigram Language Models and Reevaluation Strategy for Improved Recognition of Online Handwritten Tamil Words
TL;DR: A dynamic time-warping approach is proposed to automatically identify the parts of the online trace that discriminates between the confused classes of confused symbols, which reduces the extent of confusions between such symbols.
Proceedings ArticleDOI
Language models for online handwritten Tamil word recognition
TL;DR: On a test database of around 2000 words, it is found that bigram language models improve symbol and word recognition accuracies and while lexicon methods offer much greater improvements in terms of word recognition, there is a large dependency on choosing the right lexicon.