Tên | HMM-based Speech Synthesis with Multiple Individual Voices using Exemplar-based Voice Conversion |
Lĩnh vực | Tin học |
Tác giả | Trung-Nghia Phung |
Nhà xuất bản / Tạp chí | Năm 2017 |
Số hiệu ISSN/ISBN | |
Tóm tắt nội dung | |
Traditional text-to-speech (TTS) systems can synthesize only single individual voice. When we need to synthesize other individual voices, we have to train the system again with the new voices. The training process normally requires a huge amount of data that is usually available with a few specific voices existed in the database.
The state of the art TTS using Hidden Markov Model (HMM), called as HMM-based TTS, can synthesize speech with various voice personality characteristics by using speaker adaptation methods. However, both of the voices synthesized and adapted by HMM-based TTS are “over-smooth”. When these voices are over-smooth, the detail structures clearly linked to speaker individuality may be missing. We can also synthesize multiple voices by using some voice conversion (VC) methods combined with HMM-based TTS. However, current voice conversions still cannot synthesize target speech while keeping the detail information related to speaker individuality of the target voice and just using limited amount data of target voices. In this paper, we proposed to use exemplar-based voice conversion combined with HMM-based TTS to synthesize multiple high-quality individual voices with a few amount of target data. The evaluation results using the English data corpus CSTR confirmed the advantages of the proposed method.
Traditional text-to-speech (TTS) systems can synthesize only single individual voice. When we need to synthesize other individual voices, we have to train the system again with the new voices. The training process normally requires a huge amount of data that is usually available with a few specific voices existed in the database.The state of the art TTS using Hidden Markov Model (HMM), called as HMM-based TTS, can synthesize speech with various voice personality characteristics by using speaker adaptation methods. However, both of the voices synthesized and adapted by HMM-based TTS are “over-smooth”. When these voices are over-smooth, the detail structures clearly linked to speaker individuality may be missing. We can also synthesize multiple voices by using some voice conversion (VC) methods combined with HMM-based TTS. However, current voice conversions still cannot synthesize target speech while keeping the detail information related to speaker individuality of the target voice and just using limited amount data of target voices. In this paper, we proposed to use exemplar-based voice conversion combined with HMM-based TTS to synthesize multiple high-quality individual voices with a few amount of target data. The evaluation results using the English data corpus CSTR confirmed the advantages of the proposed method. |
|
Đính kèm:
|
- Nâng cao hiệu quả kỹ năng hoạt động xã hội cho sinh viên ở các trường đại học sư phạm
- Quản lý hoạt động đánh giá kết quả học tập của sinh viên ở trường đại học theo Chuẩn đầu ra
- ORIENTATION OF INFORMATION TECHNOLOGY APPLICATION IN EDUCATION OF NATIONAL DEFENSE AND SECURITY FOR STUDENTS IN VIETNAM
- The Importance of National Defense Education in Quality Education for College Students in Viet Nam
- National Defense Education for College Students in Viet Nam from the Perspective of Comprehensive Security
- Nghiên cứu phát triển phương pháp mô hình hóa toán học để giải quyết các vấn đề về phân lớp đối tượng dựa trên kỹ thuật thị giác máy tính và phương pháp học sâu, ứng dụng trong bài toán phân loại các khuyết tật mặt đường (Chủ nhiệm: admin_cntt&tt)
- Nghiên cứu và xây dựng mô hình dự đoán vị trí Protein SUMOylation (Chủ nhiệm: admin_cntt&tt)
- Chuyển đổi số các hiện vật tại Bảo tàng tỉnh Yên Bái hình thành Bảo tàng thực tế ảo (VR) (Chủ nhiệm: admin_cntt&tt)
- Tên đề tài: Xây dựng hệ thống tái hiện 3D di tích lịch sử Đồi A1, TP. Điện Biên Phủ nhằm hỗ trợ phát triển và quảng bá du lịch (Chủ nhiệm: admin_cntt&tt)
- Xây dựng cơ sở dữ liệu trực tuyến phục vụ phát triển kinh tế, xã hội tỉnh Thái Nguyên (Chủ nhiệm: admin_cntt&tt)
- Hoạt động xã hội...
- Chuẩn đầu ra...
- Education; College Students; National Defense Education; Information Technology Application.
- College Students; National Defense Education; Quality Education.
- Comprehensive Security Concept; college Students; National Defense Awareness.
- National Defense Education Section; Optimization Principle; Teaching Method.
- Military Theory Teaching; College Students; Quality Education.
- Information age; National defense education; Innovation
- information technology
- fostering