Search

A new modular recurrent neural network (MRNN)-based speech-recognition method that can recognize the entire vocabulary of 1280 highly confusable Mandarin syllables is proposed in this paper. The basic idea is to first split the complicated task, in both feature and temporal domains, into several much simpler subtasks involving subsyllable and tone discrimination, and then to use two weighting RNN's to generate several dynamic weighting functions to integrate the subsolutions into a complete solution. The novelty of the proposed method lies mainly in the use of appropriate a priori linguistic knowledge of simple initial-final structures of Mandarin syllables in the architecture design of the MRNN. The resulting MRNN is therefore effective and efficient in discriminating among highly confusable Mandarin syllables. Thus both the time-alignment and scaling problems of the ANN-based approach for large-vocabulary speech-recognition can be addressed. Experimental results show that the proposed method and its extensions, the reverse-time MRNN (Rev-MRNN) and bidirection MRNN (Bi-MRNN), all outperform an advanced HMM method trained with the MCE/GPD algorithm in both recognition-rate and system complexity. Index Terms - Mandarin speech recognition, MCE/GPD algorithms, modular recurrent neural networks.

Emotions are an integral part of human interactions and are significant factors in determining user satisfaction or customer opinion. speech emotion recognition (SER) modules also play an important role in the development of human–computer interaction (HCI) applications. A tremendous number of SER systems have been developed over the last decades. Attention-based deep neural networks (DNNs) have been shown as suitable tools for mining information that is unevenly time distributed in multimedia content. The attention mechanism has been recently incorporated in DNN architectures to emphasise also emotional salient information. This paper provides a review of the recent development in SER and also examines the impact of various attention mechanisms on SER performance. Overall comparison of the system accuracies is performed on a widely used IEMOCAP benchmark database. [ABSTRACT FROM AUTHOR]

Online Q&A forums, unlike search engines, allow posting of various types of queries, thus attracting users to seek information and solve problems in specific domains. However, as insufficient knowledge leads to incomprehensible queries, unsuitable responses are common. We develop posting recommendation systems (RSs) to support users in composing reasonable posts and receiving effective answers. The posting RSs were evaluated by a user study containing 27 participants and three tasks to examine if users engaged more in the question generation process. Two medical experts were recruited to verify whether professionals can understand and answer posts supported by RSs. The results show that the proposed mechanism enables askers to produce posts with better understandability, which leads experts to devote more attention to answer their questions. [ABSTRACT FROM AUTHOR]