Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
In concatenative synthesis for English, scarcity of speech data for many contexts is a serious problem. The authors propose a novel unit selection scheme ...
In concatenative speech synthesis for English, scarcity of speech data for many contexts is a serious problem. In this paper, we propose a new unit ...
In this paper we propose a new unit selection scheme using broad descriptive phonetic categories (i.e. a dis- tinctive feature set) and suprasegmental features ...
A novel unit selection scheme using a decision-tree-based clustering method that combines acoustic and linguistic knowledge with statistical modeling is ...
People also ask
This algorithm works in three stages: 1. From a general speech databases, build a cluster tree as one would when creating a unit selection voice. 2.
This paper begins by discussing the advantages and disadvantages of the decision tree and non-decision tree approaches to unit selection synthesis.
In this study, a unit selection method based on tree-structured clustering of data is implemented and evaluated. This approach to tree construction differs from ...
While the two-pass decision tree approach outperformed the factorized decision tree approach in an emphasis synthesis test, the latter led to significantly.
Jan 18, 2017 · Decision Trees and H(S)MMs. HMM-based TTS systems depend on two elements: HMMs and decision trees [Yoshimura et al. 1999]. The HMMs (HSMMs in ...
Dec 16, 2019 · This work introduces a unit selection-based text-to-speech-and-singing (US-TTS&S) synthesis framework, which integrates speech-to-singing (STS) ...