著者

Shinnosuke Takamichi Ryosuke Sonobe Kentaro Mitsui Yuki Saito Tomoki Koriyama Naoko Tanji Hiroshi Saruwatari

出版者

ACOUSTICAL SOCIETY OF JAPAN

雑誌

Acoustical Science and Technology (ISSN:13463969)

巻号頁・発行日

vol.41, no.5, pp.761-768, 2020-09-01 (Released:2020-09-01)

参考文献数

50

被引用文献数

17

---

In this paper, we develop two corpora for speech synthesis research. Thanks to improvements in machine learning techniques, including deep learning, speech synthesis is becoming a machine learning task. To accelerate speech synthesis research, we aim at developing Japanese voice corpora reasonably accessible from not only academic institutions but also commercial companies. In this paper, we construct the JSUT and JVS corpora. They are designed mainly for text-to-speech synthesis and voice conversion, respectively. The JSUT corpus contains 10 hours of reading-style speech uttered by a single speaker, and the JVS corpus contains 30 hours containing three styles of speech uttered by 100 speakers. This paper describes how we designed the corpora and summarizes the specifications. The corpora are available at our project pages.

著者

Hiroki TAMARU Yuki SAITO Shinnosuke TAKAMICHI Tomoki KORIYAMA Hiroshi SARUWATARI

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E103.D, no.3, pp.639-647, 2020-03-01 (Released:2020-03-01)

参考文献数

32

被引用文献数

3

---

This paper proposes a generative moment matching network (GMMN)-based post-filtering method for providing inter-utterance pitch variation to singing voices and discusses its application to our developed mixing method called neural double-tracking (NDT). When a human singer sings and records the same song twice, there is a difference between the two recordings. The difference, which is called inter-utterance variation, enriches the performer's musical expression and the audience's experience. For example, it makes every concert special because it never recurs in exactly the same manner. Inter-utterance variation enables a mixing method called double-tracking (DT). With DT, the same phrase is recorded twice, then the two recordings are mixed to give richness to singing voices. However, in synthesized singing voices, which are commonly used to create music, there is no inter-utterance variation because the synthesis process is deterministic. There is also no inter-utterance variation when only one voice is recorded. Although there is a signal processing-based method called artificial DT (ADT) to layer singing voices, the signal processing results in unnatural sound artifacts. To solve these problems, we propose a post-filtering method for randomly modulating synthesized or natural singing voices as if the singer sang again. The post-filter built with our method models the inter-utterance pitch variation of human singing voices using a conditional GMMN. Evaluation results indicate that 1) the proposed method provides perceptible and natural inter-utterance variation to synthesized singing voices and that 2) our NDT exhibits higher double-trackedness than ADT when applied to both synthesized and natural singing voices.