Optical Music Recognition (OMR) is an important technology within Music Information Retrieval. Deep learning models show promising results on OMR tasks, but symbol-level annotated data sets of sufficient size to train such models are not available and difficult to develop. We present a deep learning architecture called a Convolutional Sequence-to-Sequence model to both move towards an end-to-en...

In this work we present a state-of-the-art approach for unconstrained natural scene text recognition. We propose a cascade approach that incorporates a convolutional neural network (CNN) architecture followed by a long short term memory model (LSTM). The CNN learns visual features for the characters and uses them with a softmax layer to detect sequence of characters. While the CNN gives very go...

Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners. Recent innovations in Deep Learning have given rise to an alternative – discriminative models called Sequence-to-Sequence models, that can almost match the accur...

The effect of glycerol on the specificity of DNA cleavage by the restriction endonuclease BamHI has been examined. In addition to the canonical G decreases from G-A-T-C-C site, BamHI cuts DNA at several sites that we have named noncanonical BamHI.1 sites. The number of BamHI.1 sites in simian virus 40 and pBR322 was determined to be 13 for each DNA. Cutting sites determined by DNA sequence anal...

In this work, we conduct a detailed evaluation of various allneural, end-to-end trained, sequence-to-sequence models applied to the task of speech recognition. Notably, each of these systems directly predicts graphemes in the written domain, without using an external pronunciation lexicon, or a separate language model. We examine several sequence-to-sequence models including connectionist tempo...

This PhD thesis investigates the image sequence labeling problems optical character recognition (OCR), object tracking, and automatic sign language recognition (ASLR). To address these problems we investigate which concepts and ideas can be adopted from speech recognition to these problems. For each of these tasks we propose an approach that is centered around the approaches known from speech r...

We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution [Graves et al. (2006)] which uses CTC output layer, our approach makes minimalistic assumptions on the structure and length of the sequence. We use a two step encoder-decoder approach – (a) A recur...

End-to-end multi-talker speech recognition is an emerging research trend in the community due to its vast potential applications such as conversation and meeting transcriptions. To best of our knowledge, all existing works are constrained offline scenario. In this work, we propose Streaming Unmixing Recognition Transducer (SURT) for end-to-end recognition. Our model employs Recurrent Neural Net...