In this paper, we present criteria of objective measurement of speech quality to provide the mobile-VoIP services efficiently over wireless mobile internet. The mobile-VoIP service, which is based on mobility and is error-prone compared to conventional VoIP over wired network, is about to be launched, but there have not been adequate quality indexes and the Quality of Service (QoS) standards for evaluating speech quality of Mobile-VoIP. In addition, there are many factors influencing on the speech quality in packet network of which packet loss contribute directly to the overall voice communication quality. For this reason, we adopt the Gilbert-Elliot Channel Model for modeling packet network based on IP and assess the voice quality through the objective speech method of ITU-T P. 862 PESQ and ITU-T P. 862.1 MOS-LQO under various packet loss rates in the transmission channel environments. Our simulation results address the specific criteria and QoS for the mobile-VoIP services in terms of the various packet loss environments.

To get more natural synthetic speech generated by a Korean TTS (Text-To-Speech) system, we have to know all the possible prosodic rules in Korean spoken language. We should find out these rules from linguistic, phonetic information or from real speech. In general, all of these rules should be integrated into a prosody-generation algorithm in a TTS system. But this algorithm cannot cover up all the possible prosodic rules in a language and it is not perfect, so the naturalness of synthesized speech cannot be as good as we expect. ANNs (Artificial Neural Networks) can be trained to learn the prosodic rules in Korean spoken language. To train and test ANNs, we need to prepare the prosodic patterns of all the phonemic segments in a prosodic corpus. A prosodic corpus will include meaningful sentences to represent all the possible prosodic rules. Sentences in the corpus were made by picking up a series of words from the list of PB (phonetically Balanced) isolated words. These sentences in the corpus were read by speakers, recorded, and collected as a speech database. By analyzing recorded real speech, we can extract prosodic pattern about each phoneme, and assign them as target and test patterns for ANNs. ANNs can learn the prosody from natural speech and generate prosodic patterns of the central phonemic segment in phoneme strings as output response of ANNs when phoneme strings of a sentence are given to ANNs as input stimuli.

Mutual radiation impedance becomes more important in the design and analysis of acoustic transducers for higher power, better beam pattern, and wider bandwidth at low frequency sonar systems. This review paper focused on literature survey about the researches of mutual radiation impedance in the acoustic transducer arrays over 60 years. The papers of mutual radiation impedance were summarized in terms of transducer array structures on various baffle geometries such as planar, cylindrical, spherical, conformal, spheroidal, and elliptic cylindrical arrays. Then the computation schemes of solving conventional quadruple integral in the definition of mutual radiation impedance were surveyed including spatial convolution method, which reduces the quadruple integral to a double integral for efficient computation.

The present study aims to investigate the effects of sound diffusers and absorbers on the sound clarity in classrooms. In order to do this, computer simulations were carried out to find the effective area of treatment which could enhance the sound clarity in the room. Acoustic measurements were undertaken in a lecture room with several conditions changing the surface of walls and ceilings with diffusers and absorbers. Diffusion and absorption treatments were applied to the side walls, rear wall and the ceiling of the classroom. SPL, RT, D50, RASTI were measured at 9 measurement points with one sound source and MLS was used as the sound source signal. The results show that higher sound clarity was obtained when diffusers were applied to rear walls and ceiling rather than side walls. Also, it was confirmed that absorption increased sound clarity more effectively with smaller amount in comparison with diffusers. It was also concluded that the effects of sound diffusers and absorbers on the sound clarity could be obtained distinctly at the rear area of the classroom.

In practical applications of speech recognition, one of the fundamental questions might be on the number of training data that should be provided for a specific task. Though plenty of training data would undoubtedly enhance the system performance, we are then faced with the problem of heavy cost. Therefore, it is of crucial importance to determine the least number of training data that will afford a certain level of accuracy. For this purpose, we investigate the effect of the number of training data on the speaker-independent speech recognition of isolated words by using FVQ/HMM. The result showed that the error rate is roughly inversely proportional to the number of training data and grows linearly with the vocabulary size.

Heart sound segmentation into its components, S1, systole, S2 and diastole is the first step of analysis and the most important part in the automatic diagnosis of heart sounds. Conventionally, the Shannon energy envelope peak detection method has been popularly used due to its superior performance in locating S1 and S2. Recently, the HMM has been shown to be quite suitable in modeling the heart sound signal and its use in segmenting the heart sound signal has been suggested with some success. In this paper, we compared the two methods for heart sound segmentation using a common database. Experimental tests carried out on the 4 different types of heart sound signals showed that the segmentation accuracy relative to the manual segmentation was 97.4% in the HMM based method which was larger than 91.5% in the peak detection method.