http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Najeeb Ullah Khan (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
Singing Voice Synthesis Using HMM Based TTS and MusicXML
Najeeb Ullah Khan(칸 나지브 울라),Jung-Chul Lee(이정철) 한국컴퓨터정보학회 2015 韓國컴퓨터情報學會論文誌 Vol.20 No.5
노래음 합성이란 주어진 가사와 악보를 이용하여 컴퓨터에서 노래음을 생성하는 것이다. 텍스트/음성 변환기에 널리 사용된 HMM 기반 음성합성기는 최근 노래음 합성에도 적용되고 있다. 그러나 기존의 구현방법에는 대용량의 노래음 데이터베이스 수집과 학습이 필요하여 구현에 어려움이 있다. 또한 기존의 상용 노래음 합성시스템은 피아노 롤 방식의 악보 표현방식을 사용하고 있어 일반인에게는 익숙하지 않으므로 읽기 쉬운 표준 악보형식의 사용자 인터페이스를 지원하여 노래 학습의 편의성을 향상시킬 필요가 있다. 이 문제를 해결하기 위하여 본 논문에서는 기존 낭독형 음성합성기의 HMM 모델을 이용하고 노래음에 적합한 피치값과 지속시간 제어방법을 적용하여 HMM 모델 파라미터 값을 변화시킴으로서 노래음을 생성하는 방법을 제안한다. 그리고 음표와 가사를 입력하기 위한 MusicXML 기반의 악보편집기를 전단으로, HMM 기반의 텍스트/음성 변환 합성기를 합성기 후단으로서 사용하여 노래음 합성시스템을 구현하는 방법을 제안한다. 본 논문에서 제안하는 방법을 이용하여 합성된 노래음을 평가하였으며 평가결과 활용 가능성을 확인하였다. Singing voice synthesis is the generation of a song using a computer given its lyrics and musical notes. Hidden Markov models (HMM) have been proved to be the models of choice for text to speech synthesis. HMMs have also been used for singing voice synthesis research, however, a huge database is needed for the training of HMMs for singing voice synthesis. And commercially available singing voice synthesis systems which use the piano roll music notation, needs to adopt the easy to read standard music notation which make it suitable for singing learning applications. To overcome this problem, we use a speech database for training context dependent HMMs, to be used for singing voice synthesis. Pitch and duration control methods have been devised to modify the parameters of the HMMs trained on speech, to be used as the synthesis units for the singing voice. This work describes a singing voice synthesis system which uses a MusicXML based music score editor as the front-end interface for entry of the notes and lyrics to be synthesized and a hidden Markov model based text to speech synthesis system as the back-end synthesizer. A perceptual test shows the feasibility of our proposed system.
-
Development of a Music Score Editor based on MusicXML
이정철(Najeeb Ullah Khan),칸 나지브 울라(Jung-Chul Lee) 한국컴퓨터정보학회 2014 韓國컴퓨터情報學會論文誌 Vol.19 No.2
과거 작곡가들은 피아노, 바이올린, 기타, 플롯, 드럼과 같은 고전적 악기나 일반적인 도구들을 이용하여 작곡하였다. 그러나 디지털 기술의 발전으로 많은 소프트웨어 응용 프로그램이 개발되었으며 이제 음악가들은 개인용 컴퓨터를 이용하여 곡들을 제작할 수 있게 되었다. NIFF, SMDL, 그리고 MIDI와 같은 다양한 악보 표현 형식이 제안되었으나 MIDI 형식이 성공적으로 사용되어 왔다. 최근에는 MusicXML 형식이 컴퓨터 음악을 표현하는 사실상 표준으로 부상하였다. 본 논문에서는 MusicXML 형식의 구조에 대한 개요를 기술하고 C# 언어로 MusicXML 기반 악보 편집 소프트웨어를 구현하는 방법을 제안한다. 본 논문에서 제안하는 방법을 이용하여 악보 편집 소프트웨어를를 구현함으로써 구현의 효율성을 보였으며 활용 가능성을 확인하였다. In the past composers used to make music with classical instruments such as piano, violin, guitar, flute, drums, and other well-known tools. With the advent of digital technology many software programs were developed which allow musicians to compose tunes using personal computers. Many file formats were introduced such as NIFF, SMDL and MIDI but none besides MIDI has been successful. Recently MusicXML has emerged as a de-facto standard for the computer representation of music. This paper presents a brief description of the structure of the MusicXML format and describes the development of a music score editor based on MusicXML. We implemented a MusicXML-based score editing software using C# language and a feasibility test showed the efficiency of our proposed method.
-
Measurement of Traffic-Related Air Pollution in Peshawar, Pakistan - A Pilot Study
Mohsin Khan,Mohammad Abdul Aziz Irfan,Najeeb Ullah 한국대기환경학회 2021 Asian Journal of Atmospheric Environment (AJAE) Vol.15 No.4
This pilot study measured Traffic-Related Air Pollution (TRAP) and calculated the corresponding Air Quality Index (AQI) in Peshawar. Using Libelium wireless sensors, the research measured outdoor TRAP and monitored indoor air quality for 48 days. The maximum outdoors daily mean concentration was 47 μg m-3 for PM1, 90 μg m-3 for PM2.5, 356 μg m-3 for PM10, 258 ppb for SO2, and 219 ppb for NO2, respectively. This corresponds to PM2.5 AQI of 158 (Unhealthy), PM10 AQI of 148 (Unhealthy for Sensitive Groups; USG), SO2 AQI of 181 (Unhealthy), and NO2 AQI of 123 (USG). The maximum daily average concentration for the indoor condition was 31 μg m-3 for PM1, 49 μg m-3 for PM2.5, 78 μg m-3 for PM10, 465 ppb for SO2, and 247 ppb for NO2, respectively. The corresponding AQI was 135 (USG) for PM2.5, 62 (Moderate) for PM10, 254 (Very Unhealthy) for SO2, and 129 (USG) for NO2. Data analysis shows that about 73% of the overall indoor AQI falls in the category of “USG”, while SO2 was the largest contributor to overall AQI. The study concludes that indoor AQI was slightly better than outdoor AQI because of the distance and height from the outdoor location. Moreover, Pakistan’s AQI for PM2.5 exceeds WHO’s 24-hours limit; however, it was relatively better by 23%, 65%, and 170% compared to China, India, and Bangladesh, respectively. In contrast, AQI for SO2 and NO2 was poor as compared to the same countries. The concentration and AQI for traffic-related air pollutants remain unhealthy and sometimes becomes hazardous, which means the sensitive groups are at greater risk.
-
Jianyin Xie,Fengmei Li,Najeeb Ullah Khan,Xiaoyang Zhu,Xueqiang Wang,Zhifang Zhang,Xiaoqian Ma,Yan Zhao,Quan Zhang,Shuyang Zhang,Zhanying Zhang,Jinjie Li,Zichao Li,Hongliang Zhang 한국유전학회 2019 Genes & Genomics Vol.41 No.3
Introduction As one of the main yield components, grain number per panicle (GNP) played critical role in the rice yield improvement. The identification of natural advantageous variations under different situations will promote the sustainable genetic improvement in rice yield. Objectives This study was designed to identify natural genotypes in a rice mini-core collection, to examine the genotypic effects across the indica and japonica genetic background in different environments, and excavating the superior genotypes that had drove the modern genetic improvement. Methods The association mapping of GNP was carried out using a mini-core collection including 154 indica and 119 japonica accessions in seven different environments. Genotypic effects of each genotype for each QTL were calculated and genotype frequency distortion between the commercial rice cultivars and landraces was screened by χ2-test. Results In total, 74 QTLs containing stable and sensitive QTLs in various environments were detected. Within them, 20 positive and 24 negative genotypes in indica, and 24 positive and 16 negative genotypes in japonica were identified. When checking the accumulation of positive genotypes identified in indica across cultivars in each of the two subspecies, it indicated that increased number of positive genotypes identified in indica results in the substantially increased GNP in both indica and japonica across all of the environments, while this trend was not obvious for the positive genotypes identified in japonica especially in short day environments. Moreover, the positive and negative genotype frequency distortion between the landraces and commercial rice cultivars indicated that both positive selection of positive genotypes and negative selection of negative genotypes had driven the genetic improvement on GNP. Conclusion Our findings suggested that the accumulation of positive genotypes and purifying negative genotypes played equivalently important roles in the improvement of rice yield, but the efficient use for some QTLs or genotypes depends on the comprehensive evaluation of their effect under diverse genetic backgrounds and environments.
ScienceON
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
