Search

Abstract Handwritten document transcription aims to obtain the contents of a document to provide efficient information access to, among other, digitised historical documents. The increasing number of historical documents published by libraries and archives makes this an important task. In this context, the use of image processing and understanding techniques in conjunction with assistive technologies reduces the time and human effort required for obtaining the final perfect transcription. The assistive transcription system proposes a hypothesis, usually derived from a recognition process of the handwritten text image. Then, the professional transcriber feedback can be used to obtain an improved hypothesis and speed-up the final transcription. In this framework, a speech signal corresponding to the dictation of the handwritten text can be used as an additional source of information. This multimodal approach, that combines the image of the handwritten text with the speech of the dictation of its contents, could make better the hypotheses (initial and improved) offered to the transcriber. In this paper we study the feasibility of a multimodal interactive transcription system for an assistive paradigm known as Computer Assisted Transcription of Text Images. Different techniques are tested for obtaining the multimodal combination in this framework. The use of the proposed multimodal approach reveals a significant reduction of transcription effort with some multimodal combination techniques, allowing for a faster transcription process. [ABSTRACT FROM AUTHOR]

Abstract: The transcription of historical documents is one of the most interesting tasks in which Handwritten Text Recognition can be applied, due to its interest in humanities research. One alternative for transcribing the ancient manuscripts is the use of speech dictation by using Automatic Speech Recognition techniques. In the two alternatives similar models (Hidden Markov Models and n-grams) and decoding processes (Viterbi decoding) are employed, which allows a possible combination of the two modalities with little difficulties. In this work, we explore the possibility of using recognition results of one modality to restrict the decoding process of the other modality, and apply this process iteratively. Results of these multimodal iterative alternatives are significantly better than the baseline uni-modal systems and better than the non-iterative alternatives. [Copyright &y& Elsevier]

In dialogue systems it is important to label the dialogue turns with dialogue-related meaning. Each turn is usually divided into segments and these segments are labelled with dialogue acts (DAs). A DA is a representation of the functional role of the segment. Each segment is labelled with one DA, representing its role in the ongoing discourse. The sequence of DAs given a dialogue turn is used by the dialogue manager to understand the turn. Probabilistic models that perform DA labelling can be used on segmented or unsegmented turns. The last option is more likely for a practical dialogue system, but it provides poorer results. In that case, a hypothesis for the number of segments can be provided to improve the results. We propose some methods to estimate the probability of the number of segments based on the transcription of the turn. The new labelling model includes the estimation of the probability of the number of segments in the turn. We tested this new approach with two different dialogue corpora: SwitchBoard and Dihana. The results show that this inclusion significantly improves the labelling accuracy. [ABSTRACT FROM PUBLISHER]