Narrow Results

A Phonetic Engine (PE), phonetic-level speech recognition system for continuous speech of a regional language named Punjabi, has been proposed in this paper. Punjabi is a highly prosodic language and a very small amount of work has been done in this direction on this language. As a first step towards the development of PE, 25 hrs of data is collected in three different modes, namely, Read Speech, Conversational Speech and Lecture Speech. The 10 hrs of collected data is then manually transcribed using International Phonetic Alphabet (IPA) chart. The architecture of the PE includes three different phases: data preparation, system training and system testing. Initially, the vocabulary of 49 phones is chosen by carefully analyzing the symbol frequency in IPA transcription and data files are prepared to train the system accordingly. The prepared data files and speech files are then used for modeling and feature extraction. In the development of PE, Mel Frequency Cepstral Coefficient (MFCC) is used as a feature extraction technique and Hidden Markov Model (HMM) as a classifier. The PE is developed using HTK Toolkit. The performance of PE is evaluated using three different approaches: (i) by increasing the amount of data from 3 hrs to 5 hrs, (ii) by decreasing the number of symbols from 49 to 29 and (iii) by increasing MFCC dimensions from 12 to 36. An accuracy of 72.3% has been achieved in this work when 5 hrs data with 29 symbols and 12 MFCCs was employed.

In this paper, a new phonetic alphabet called PUNJARPAbet for speech processing in the Punjabi language has been designed. The new phonetic coding scheme PUNJARPAbet developed in this paper has been primarily designed to encode the text and speech corpora recently developed by the authors in the Punjabi language. This recently developed corpus has at least 20 special features. PUNJARPAbet is capable of coding examples related to all special features of the new corpus. PUNJARPAbet is an all upper-case coding scheme and is consistent with the all upper-case version of the famous coding scheme ARPAbet developed by the Advanced Research Projects Agency (ARPA). The new scheme is very easy to follow, and is the most suitable scheme for typing on an ordinary computer keyboard as well as an ordinary typewriter. Unlike many other schemes such as the famous International Phonetic Alphabet (IPA), the PUNJARAbet is free from the laborious, irritating, and time-consuming necessities for dealing with the special symbols. It has been clearly demonstrated in this paper that PUNJARPAbet is a versatile, efficient and convenient coding scheme for not only the Punjabi language, but also any language which has sounds similar to the ones found in the Punjabi speech.

Proteome Systems Develops Ovarian Tumor Detection Kit.

Pharmaxis Closer to Market Aridol.

Acrux Receives Milestone Payment from VIVUS.

Biota Raises Funds from Share Purchase Plan.

GSK's Strategic Investment in China.

Aurobindo Pharma Obtains FDA Approval for Mirtazapine Tablets.

IPA Urges for Prudent Patent Legislation.

Zonegran Shown to Reduce Seizures in Infants.

Takeda Pushes for New Drug Application for Ramelteon.

Takeda Collaborates with Sucampo on Constipation Drug.

Eisai Gains Access to MultiCell's Hepatocyte Technology.

SiMEMS Signs International Agreement to Further Develop Revolutionary DNA Chip.

E-learning platforms (ELPs) are revolutionizing the higher education system, as they offer tremendous potential to fulfill instructional plans, safeguard students’ learning rights, and improve teaching quality. Higher education institutions (HEIs) have to consider the selection of ELPs from an organizational perspective, which involves multiple stakeholders like university administrators, students, and educators. Therefore, one can take the ELP selection as a complex multi-criteria decision-making (MCDM) problem. This research proposes a new hybrid MCDM approach on the basis of the fuzzy analytic hierarchy process (FAHP) and the evaluation based on distance from the average solution (EDAS) method to select the best ELPs. First, from the organizational perspective, we extend the technology-organization-environment (TOE) framework by adding an auxiliary resource (AR) dimension and define and prioritize 4 criteria and 14 criteria for evaluating and selecting ELPs. Second, the study uses the fuzzy set theory to process the language evaluation of experts, the FAHP method to determine criteria and sub-criteria weights, and EDAS to rank the alternatives. Finally, based on the importance-performance analysis (IPA) method, we identify the most appropriate strategic options for enhancing competitiveness. Three practical cases of China’s ELP evaluation validate the proposed model’s applicability and superiority by comparing to the two other classic evaluation models. In addition, through analysis, we obtain some encouraging results that provide some references for universities to formulate ELP selection policies and offer suggestions for platform producers to further optimize the design.