TAILIEUCHUNG - Improving the naturalness of concatenative vietnamese speech synthesis under limited data conditions

Building a large speech corpus is a costly and time-consuming task. Therefore, how to build high-quality speech synthesis under limited data conditions is an important issue, specifically for under-resourced language like Vietnamese. As the most natural-sounding speech synthesis is currently concatenative speech synthesis (CSS), it is the target speech synthesis under study in this research. All possible units of a specific phonetic unit set are required for CSS. | Journal of Computer Science and Cybernetics, , (2015), 1–16 DOI: IMPROVING THE NATURALNESS OF CONCATENATIVE VIETNAMESE SPEECH SYNTHESIS UNDER LIMITED DATA CONDITIONS PHUNG TRUNG NGHIA1 , LUONG CHI MAI2 AND MASATO AKAGI3 1 Thai 2 Institute Nguyen University of Information and Communication Technology; of Information Technology, Vietnam Academy of Science and Technology; 3 Japan Advanced Institute of Science and Technology. Email: ptnghia@ Abstract. Building a large speech corpus is a costly and time-consuming task. Therefore, how to build high-quality speech synthesis under limited data conditions is an important issue, specifically for under-resourced language like Vietnamese. As the most natural-sounding speech synthesis is currently concatenative speech synthesis (CSS), it is the target speech synthesis under study in this research. All possible units of a specific phonetic unit set are required for CSS. This requirement might be easy for verbal languages, in which the number of all units of a specific phonetic unit set such as phoneme is relatively small. However, the numbers of all tonal phonetic units are significant in tonal languages, and it is difficult to design a small corpus covering all possible tonal phonetic units. Additionally, as all context-dependent phonetic units are required to ensure the naturalness of corpus-based CSS, it needs a large database with a size up to dozens of gigabytes for concatenation. Therefore, the motivation for this work is to improve the naturalness of CSS under limited data conditions, and both of these two mentioned problems are solved. First, the authors attempt to reduce the number of tonal units required for the CSS of tonal languages by using a method of tone transformation and second to reduce mismatch-context errors in concatenation regions to make the CSS available if matching-context units could not be found from the database. Temporal Decomposition (TD), which is an .

• Kỹ thuật lập trình
• Concatenative speech synthesis
• Temporal decomposition
• Co articulation
• Tone transformation
• Limited data
• Vietnamese speech
• Neural network based tonal feature
• Vietnamese speech recognition
• Multi space distribution model
• Multi Space Distribution Hidden Markov Model
• Vietnamese Automatic Speech recognition
• Automatic speech recognition
• Vietnamese corpora
• Existing ASR systems
• Acoustic model training
• Machine learning
• Recognizing Vietnamese speech
• Speech recognition
• Multipart form data
• Multipart/form data POST request code
• The SpeechCollect app
• Large vocabulary continuous speech recognition
• Language model adaptation
• Bottleneck feature
• Mel frequency cepstral coefficients
• Deep learning
• Vietnamese speech synthesis
• Text To Speech system
• Voice response systems
• Deep neural network
• Machine translation
• Text to speech
• Ethnic minority language
• Muong dialects
• Unwritten languages
• Cross lingual speech synthesis
• The corpus based Vietnamese text to speech system
• The corpus based Vietnamese text
• Text tos peech
• ITU T P
• 85 standard
• Voice of Southern Vietnam
• Journal of Computer Science and Cybernetics
• Improving bottleneck features
• Vietnamese large vocabulary continuous speech recognition system
• Deep neural networks
• Voice of Vietnam channel
• Context dependent
• Speech parameterization
• Statistical parametric speech synthesis
• Hidden Markov Models
• Mel frequency cepstral coefficient
• Fundamental frequency
• Speech synthesis
• Hidden Markov model
• TTS systems
• Vietnamese speech recognition system
• Customer service call center
• Time delay deep neural network
• Syllable based language model
• Voice activity detection
• Journal of Automation and Control Engineering
• Speech recognition in human computer interactive control
• Computer interactive control
• HTK and Sphinx
• Human computer interaction
• Transcription system
• Force alignment procedure
• Discriminative training
• State of the art Vietnamese ASR
• Khoa học máy tính
• Tạp chí khoa học
• Part of speech tagger
• Natural Language Processing
• Stanford POS Tagger
• The conflict between copyright and freedom of speech
• The conflict between copyright
• Intellectual property right
• Explores current legal solutions
• Suggestions for Vietnamese law
• Speaking skill
• English majors
• Speech training
• Learners’ performance
• Vietnamese ESL
• Journal of science
• Learner content interaction
• English learning course at a Vietnamese university
• English learning course
• Infancy like Vietnam
• Providing continuous technical support
• Sociolinguistic phenomenon
• Phenomenon enters
• High qualified people
• English fluently
• Speech community
• Code switching
• Điện
• Điện tử
• kỹ thuật viễn thông
• cơ khí
• chế tạo máy
• hóa học
• Nhận dạng tiếng nói tiếng Việt
• Áp dụng bottle neck feature
• Bottle neck feature
• Nhận dạng tiếng Việt
• Mô hình Markov ẩn
• Sentiment analysis
• Aspect based sentiment analysis
• Text analysis
• Vietnamese Language and Speech Processing
• Summary of Doctoral Thesis Linguistics
• Doctoral Thesis Summary
• Doctoral Thesis Linguistics
• The means of expressing modality
• Direct ask questions
• Acting indirect questions
• Keyword spotting
• Far field distance
• Convolutional neural networks
• Recurrent neural networks
• Pronunciation problems
• Major errors
• Possible reasons
• English majoring students
• Vietnamese learners’ speech organs