A New Approach to Zero-Crossing and LPC Speech Detection for Low Power Terminals Using Speech Recognition Technology

2021 ◽  
Vol 141 (12) ◽  
pp. 1424-1429
Author(s):  
Kentaro Ema ◽  
Akira Yasuda ◽  
Fumiya Oshima
2018 ◽  
Vol 2 (1) ◽  
pp. 345-353
Author(s):  
Dhimas Sena Rahmantara ◽  
Kartina Diah Kesuma Wardhani ◽  
Maksum Ro’is Adin Saf

Al-Qur’an is a scripture which contains the saying of Allah Subhanahu Wa Ta’aala and was revealed to Prophet Muhammad. The 30th juz is the juz that exists in the Al-Qur’an. When studying how to read Al-Qur’an well, the first thing that is learned is reading and memorizing surahs in the 30th juz. Nevertheless, there is a problem in remembering or knowing the surah name and the verse which are in the 30th juz. An android application was developed in order to recognize the surah names in the 30th juz by utilizing speech recognition technology to overcome that problem. Markov Model (Markov Chain) algorithm was implemented in this application. This algorithm will process user’s speech and compute probability of the surah name that was spoken. Speech detection testing gave result that the highest accuracy of application in recognizing the speeches was in the environment without noise with the accuracy of 100% in the most ideal distance is 50 cm for male and for female user. Based on the blackbox testing result, all functionalities of the application have functionated well. Control flow testing gave result that the value is 7 which indicates that the code is simple and well written. 87,74% respondents answered, by filling up the questionnaires, that the application is useful in order to make user knows better about the surah names in the 30th juz.


Author(s):  
Aliv Faizal M ◽  
Akhmad Alimudin

English pronunciation has long been taught through the delivery of phonetic symbols to study the sound of each phoneme in English. In Multimedia Broadcasting study program at Surabaya State Electronics Polytechnic, pronunciation has long been delivered to the students through guidebooks in the form of phonetic symbols that teach basic sound pronunciation in English. English teachers practice the sound of each phoneme directly to thestudents. After going through various observations based on the track record of student achievement of this pronunciation material, I as a teacher as well as researcher found that my student achievement was less than the desired target. This was due to the limited source of English pronunciation learning where students only learned face-to-face in the classroom. Through the use of English learning media of pronunciation interactively using speech recognition technology, it was expected that Multimedia Broadcasting course students in Surabaya State Electronics Polytechnic could improve their English pronunciation ability. After students complete the English pronunciation training sequence using pronunciation application using speech recognition technology, the data from the interview stated that the students felt more confident and improved their pronunciation ability and also felt the increased motivation to learn English pronunciation using English pronunciation learning app using speech recognition technology.Keywords: English pronunciation, teaching, multimedia, speech recognition technology, and pronunciation app.


2014 ◽  
Vol 596 ◽  
pp. 384-387
Author(s):  
Ge Liu ◽  
Hai Bing Zhang

This paper introduces the concept of Voice Assistant, the voice recognition service providers, several typical Voice Assistant product, and then the basic working process of the Voice Assistant is described in detail and proposed the technical bottleneck problems in the development of Voice Assistant software.


Sign in / Sign up

Export Citation Format

Share Document