Tao Jianhua

A Fast Implementation of Adaptive Histogram Equalization

Adaptive histogram equalization (AHE) is a popular and effective algorithm for image contrast enhancement. But its quite computationally expensive and time consuming. In this paper, a fast implementation of AHE based on pure software techniques is proposed. Three accelerative techniques are combined to form the new fast AHE: first, local histogram is acquired by an iterative approach with a sliding window; second, in computing cumulative histogram function, not more than half of the histogram is cumulated; Third, by keep the block size W2 equal to the product of grey level number and integral power of 2, all the multiplication and division operations are replaced with fast bitwise shift. Both theoretical analysis and experimental results demonstrate the proposed algorithm is effective

Chinese prosodic phrasing with extended features

Prosodic phrasing is an important component in modern TTS systems, which inserts natural and reasonable breaks into long utterance. This paper reports the study of prosodic phrasing in unrestricted Chinese text. A text corpus of 500 sentences is collected from our speech database and manually labeled with syntactic structure and prosodic structure. Features and target prosody labels are extracted from the corpus and used as training examples for a rule-learning program. The acquired rules are evaluated on unseen sentences. The experiments show that the tree-level syntactic features are the most effective ones for Chinese prosodic phrasing. And chunk-level features can also help to improve the prediction accuracy.

Multi-source based acoustic model for speech synthesis

Traditional source-filter model has obvious limitation for speech synthesis in pitch modification due to the lack of spectrum distortion processing. To solve the problem, the paper compares spectrum features of voice source in various F0 ranges and timbres in detail, and generates multi-source (MS) based acoustic model for speech generation in various prosodies and timbres, by classifying and reconstructing voice source into different types. The model enhances the quality of speech synthesis even with strong changing of the speaking mood. It is important for future research on personalized and embedded speech synthesis system.

Auditive learning based Chinese F0 prediction

The paper described a new F0 model based on auditive learning (AL) method. Being focused on the notion of prosody templates, we confirmed that F0 patterns for a syllable can be extracted from various anamorphosis of F0 contours in spontaneous speech. It is much suitable to use F0 templates selection method for Chinese F0 prediction with prosody cost function (PCF). Furthermore, an AL method is used to adjust the weight of PCF dynamically in application. Unlike other methods, the approach may give feedback as to exactly what are crucial parameters determining the successful choice of patterns. The paper also analyzes the error distribution of the F0 predicting results. Both smoothing testing and F0 range testing show that the synthesis results are much closed to human being.

Intelligence methods of multi-modal information fusion in human-computer interaction

We first introduce the concepts of single-modal information processing and multi-modal information fusion in cognitive science. Some classical multi-modal information fusion models and their computer implementations in history are also explained. Under the conditions that each channels information can be obtained, and their features could be unified representation synchronously, the fusion of multi-modal information can be transformed into classification or regression problems. For practical human-computer interaction systems, the performance of multi-modal information fusion largely relies on the accuracy of the single-modal information identification and the design of the interactive system. We present a practical example of multi-modal information fusion system, and discuss its performances on human computer interaction. Finally, the possible and important development trends for multi-modal human-computer interaction techniques and systems are discussed.

Football News Generation from Chinese Live Webcast Script

Challenges exist in the field of sports news generation automatically from webcast that (1) finding hot events and sentences accurately; (2) organizing the selected sentences with highly readability. This paper proposes a framework to generate sports news automatically. First, to obtain accurate hot events and sentences, we design a neural network to predict the probabilities that each statement in live webcast script appears in the writing news, where the inputs of the neural network are weighed word vectors obtained from football keywords dictionary, and the outputs the similarity of statements in training live webcast script and sentences in training news. In this way, the “good” sentences selected from webcast contribute to the semi-finished sport news. To make the generated news to be possibly similar to human writing, we adopt idioms often appeared in football game to describe or summarize the games’ development or turns between the selected sentences, and come into being the final sport news. The proposed framework are validated on the training and test data set proved by “Sports News Generation from Live Webcast scripts” task of NLPCC 2016, the experiments show that the proposed method present good performance.Challenges exist in the field of sports news generation automatically from webcast that (1) finding hot events and sentences accurately; (2) organizing the selected sentences with highly readability. This paper proposes a framework to generate sports news automatically. First, to obtain accurate hot events and sentences, we design a neural network to predict the probabilities that each statement in live webcast script appears in the writing news, where the inputs of the neural network are weighed word vectors obtained from football keywords dictionary, and the outputs the similarity of statements in training live webcast script and sentences in training news. In this way, the “good” sentences selected from webcast contribute to the semi-finished sport news. To make the generated news to be possibly similar to human writing, we adopt idioms often appeared in football game to describe or summarize the games’ development or turns between the selected sentences, and come into being the final sport news. The proposed framework are validated on the training and test data set proved by “Sports News Generation from Live Webcast scripts” task of NLPCC 2016, the experiments show that the proposed method present good performance.