Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Matthew Gibson; Teemu Hirsimäki; Reima Karhila; Mikko Kurimo; William Byrne

doi:10.1109/ICASSP.2010.5495196

Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Matthew Gibson, Teemu Hirsimäki, Reima Karhila, Mikko Kurimo, William Byrne

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

18 Citations (Scopus)

Original language	English
Title of host publication	ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Place of Publication	Dallas
Publisher	IEEE
Pages	4642-4645
ISBN (Print)	978-1-4244-4296-6
DOIs	https://doi.org/10.1109/ICASSP.2010.5495196
Publication status	Published - 2010
MoE publication type	A4 Conference publication

Publication series

Name	International Conference on Acoustics Speech and Signal Processing ICASSP
ISSN (Print)	1520-6149

Keywords

speaker adaptation
speech synthesis

Access to Document

10.1109/ICASSP.2010.5495196

Cite this

Gibson, M., Hirsimäki, T., Karhila, R., Kurimo, M., & Byrne, W. (2010). Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. In ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4642-4645). (International Conference on Acoustics Speech and Signal Processing ICASSP). IEEE. https://doi.org/10.1109/ICASSP.2010.5495196

Gibson, Matthew ; Hirsimäki, Teemu ; Karhila, Reima et al. / Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas : IEEE, 2010. pp. 4642-4645 (International Conference on Acoustics Speech and Signal Processing ICASSP).

@inproceedings{eca73dd9f2144ee98b4dd100fccfde38,

title = "Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction",

keywords = "speaker adaptation, speech synthesis, speaker adaptation, speech synthesis, speaker adaptation, speech synthesis",

author = "Matthew Gibson and Teemu Hirsim{\"a}ki and Reima Karhila and Mikko Kurimo and William Byrne",

year = "2010",

doi = "10.1109/ICASSP.2010.5495196",

language = "English",

isbn = "978-1-4244-4296-6",

series = "International Conference on Acoustics Speech and Signal Processing ICASSP",

publisher = "IEEE",

pages = "4642--4645",

booktitle = "ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

}

Gibson, M, Hirsimäki, T, Karhila, R, Kurimo, M & Byrne, W 2010, Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. in ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics Speech and Signal Processing ICASSP, IEEE, Dallas, pp. 4642-4645. https://doi.org/10.1109/ICASSP.2010.5495196

Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. / Gibson, Matthew; Hirsimäki, Teemu; Karhila, Reima et al.
ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas: IEEE, 2010. p. 4642-4645 (International Conference on Acoustics Speech and Signal Processing ICASSP).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

AU - Gibson, Matthew

AU - Hirsimäki, Teemu

AU - Karhila, Reima

AU - Kurimo, Mikko

AU - Byrne, William

PY - 2010

Y1 - 2010

KW - speaker adaptation

KW - speech synthesis

KW - speaker adaptation

KW - speech synthesis

KW - speaker adaptation

KW - speech synthesis

U2 - 10.1109/ICASSP.2010.5495196

DO - 10.1109/ICASSP.2010.5495196

M3 - Conference article in proceedings

SN - 978-1-4244-4296-6

T3 - International Conference on Acoustics Speech and Signal Processing ICASSP

SP - 4642

EP - 4645

BT - ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

CY - Dallas

ER -

Gibson M, Hirsimäki T, Karhila R, Kurimo M, Byrne W. Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. In ICASSP The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas: IEEE. 2010. p. 4642-4645. (International Conference on Acoustics Speech and Signal Processing ICASSP). doi: 10.1109/ICASSP.2010.5495196