2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015
DOI: 10.1109/icassp.2015.7178766
|View full text |Cite
|
Sign up to set email alerts
|

Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
25
0
1

Year Published

2016
2016
2019
2019

Publication Types

Select...
6
2

Relationship

6
2

Authors

Journals

citations
Cited by 17 publications
(27 citation statements)
references
References 19 publications
1
25
0
1
Order By: Relevance
“…a natural speech reference), significant improvements in subjective naturalness are obtained. However, none of the above techniques address what is perhaps the most fundamental problem of HMM-based speech synthesis: across-context averaging via decision tree clustering, which has been identified as a major contributing factor to reduced naturalness [8].…”
Section: A Related Workmentioning
confidence: 99%
“…a natural speech reference), significant improvements in subjective naturalness are obtained. However, none of the above techniques address what is perhaps the most fundamental problem of HMM-based speech synthesis: across-context averaging via decision tree clustering, which has been identified as a major contributing factor to reduced naturalness [8].…”
Section: A Related Workmentioning
confidence: 99%
“…In statistical parametric speech synthesis (SPSS), the vocoder has been identified a cause of "buzziness" and "phasiness" [1].…”
Section: Introductionmentioning
confidence: 99%
“…HMM 기반의 SPSS 방식에서 합성 음성의 품질을 저하시키는 원인 중의 하나는 문맥 요인을 포함시키는 음향 모델링의 구성 에 있다고 알려져 있다 (Ling et al, 2015;Zen et al, 2009 (Merritt et al, 2015;Yu et al, 2011). 그러므로 회귀 트리보다 성능이 우수한 모 델을 사용하는 방법을 모색할 필요성이 제기된다.…”
Section: 서론unclassified