Speech synthesis can also be used to generate singing voices. In this regard, Hono et al. (2019) propose a DNN-based GAN and cGAN for singing voice synthesis. G gets score feature sequences and linguistic features as input and uses them to predict or generate acoustic features. In the fir...
3481 A Lightweight Change Detection Method Based on Feature Interaction and Transformer for High Resolution Remote Sensing Images 10170 A LIGHTWEIGHT HYBRID MULTI-CHANNEL SPEECH EXTRACTION SYSTEM WITH DIRECTIONAL VOICE ACTIVITY DETECTION 2931 A LIGHT-WEIGHT STATE DETECTION MODEL FOR KALMAN-FILTER-BASED ACO...
The possibility for acquisition of statistical network grammar using ergodic HMM automatic music composition, automatic music accompaniment, harmony analysis, singing voice synthesis, multipitch analysis, rhythm analysis, score following J Murakami,H Yamatomo,S Sagayama - DBLP 被引量: 3发表: 1993年 Di...