The document processing in the work of the author's R&D group is described from the viewpoints of information processing of multimedia. These include document information processing both on hardware and software. Starting from figure and background, line drawing and photograph are discussed on both real-time signal processing and presentation based on mesh measurement. Character recognition is described from the beginning of single font to the updated character images on general documents appearing in text, drawings, graphs, tables, and maps. In the case of name cards, all hierarchical analysis and processing are mentioned, including the retrieval system and experimental scores.>

We will describe a noise reduction method which diffuses and suppresses the noise component, while concentrating and enhancing speech formant information. Two Dimensional Spectral Smoothing (TDSS) is applied over a time sequence of spectral envelope to diffuse noise and concentrate formant information. After consonant enhancement, Non-linear Spectral Amplitude Transformation (NSAT) is carried out to further suppress the noise component and enhance formant information. This noise reduction method has proven to be superior to the conventional frequency subtraction method.

Recently there has been an increasing demand for high quality color pictures that can be printed using color dot printers such as ink jet or thermal transfer printers. In this paper, we consider the criteria for the good representation of color pictures and the essential points of the representation processing to satisfy these criteria. We describe a new method for the representation of color pictures based on arranging fixed size primary color dots. This method makes it possible to reproduce the original image colors without losing their smoothness or fineness.

In this paper, we describe a new model of bilevel digital images of line drawings. The key idea is that the constraints of generating the line drawings are available to select patterns which are considered to be a certain local appearance of line drawings. Concretely, when a bilevel digital image of line drawings is observed by 3 × 3 pixels' unit mesh, the patterns occurring in the unit mesh are restricted by the constraints that the digital image is line-structured. At first, lines in a digital image are strictly defined and then two assumptions related to the minimum line width and observing unit mesh are introduced. It is theoretically derived what kinds of patterns occur under these conditions and we call them ``legal patterns,'' while the other patterns not satisfying above conditions are called ``illegal patterns.'' Next, new representations such as SYM pictures and LSC pictures, which consist only of legal patterns, are proposed as a model of bilevel digital images of line drawings and the algorithms to transcribe the original bilevel digital image into the new representations in the model are introduced. Finally, the experimental results are evaluated from the viewpoint of the amount of data involved in the new representations. The results show that our theory is well-fitted to actual images and that many useful and practical applications will be derived not only in the field of documents processing, but also of digital communication.

DP matching is widely used in speech recognition. But none of the conventional formulations (Rectangular DP Matching) seem to have all the three properties: pattern commutativeness, time reversibility, and linear matching consistency. In this paper, a new formulation named "Trapezoidal DP Matching" is proposed, which preserves time reversibility and can have all the three properties. In addition, the following points are clarified; (1) The formulation gives a better approximation of continuous-time pattern distance, and is expected to improve recognition accuracy. (2) It has an effect of smoothing the weighting coefficients on local distances. (3) It provides a clear viewpoint on the relationship between weighting coefficients and the normalized time. (4) Its evaluation is reliable even for a transient portion matching.

In this paper, we describe an optimum matching method between a classified phoneme string and a phoneme string of a lexical entry in a word dictionary. This method is performed by using a phoneme similarity matrix and a dynamic programming technique. A classified segment consists of the first candidate, second candidate, reliability and duration. The effect of coarticulation is normalized in this matching procedure. We also describe a word spotting method in continuous speech by modifying this method.

This paper describes the method and the system investigated to solve the problem encountered in the automatic recognition of speech sound. From research in the automatic analyzer of speech sound, a monosyllable recognition system was constructed in which the phoneme is used as the basic recognition unit. Recently this system has been developed to accept the conversational speech sound with unlimited vocabulary. The mechanical recognition of conversational speech sound requires two basic operations. One is the segmentation of the continuous speech sound into several discrete intervals (or segments), each of which may be thought to correspond to a phoneme, and the other is the pattern recognition of such segments. For segmentation, by defining two criteria, ``stability'' and ``distance,'' the properties of the time pattern obtained by the analysis of input speech sound may be examined. The principle of the recognition is based on the mechanism of the articulation in our speech organ. Corresponding to this, the machine has the functions called phoneme classification, vowel analysis and consonant analysis. A conversational speech recognition system with the phonetic contextual approach is also applied to the vowel recognition where the time pattern of input speech is matched with the stored standard patterns in which the phonetic contextual effects are taken into consideration. The time pattern which has great variety may be effectively expressed by the new representation of ``sequential pattern'' and ``weighting pattern.''