%Aigaion2 BibTeX export from Idiap Publications %Saturday 21 December 2024 06:04:48 PM @TECHREPORT{Liang_Idiap-RR-05-2010, author = {Liang, Hui and Dines, John and Saheer, Lakshmi}, projects = {Idiap, EMIME}, month = {2}, title = {A Comparison of Supervised and Unsupervised Cross-Lingual Speaker Adaptation Approaches for HMM-Based Speech Synthesis}, type = {Idiap-RR}, number = {Idiap-RR-05-2010}, year = {2010}, institution = {Idiap}, crossref = {Liang_ICASSP_2010}, abstract = {The EMIME project aims to build a personalized speech-to-speech translator, such that spoken input of a user in one language is used to produce spoken output that still sounds like the user's voice however in another language. This distinctiveness makes unsupervised cross-lingual speaker adaptation one key to the project's success. So far, research has been conducted into unsupervised and cross-lingual cases separately by means of decision tree marginalization and HMM state mapping respectively. In this paper we combine the two techniques to perform unsupervised cross-lingual speaker adaptation. The performance of eight speaker adaptation systems (supervised vs. unsupervised, intra-lingual vs. cross-lingual) are compared using objective and subjective evaluations. Experimental results show the performance of unsupervised cross-lingual speaker adaptation is comparable to that of the supervised case in terms of spectrum adaptation in the EMIME scenario, even though automatically obtained transcriptions have a very high phoneme error rate.}, pdf = {https://publications.idiap.ch/attachments/reports/2010/Liang_Idiap-RR-05-2010.pdf} } crossreferenced publications: @INPROCEEDINGS{Liang_ICASSP_2010, author = {Liang, Hui and Dines, John and Saheer, Lakshmi}, keywords = {decision tree marginalization, HMM state mapping, unsupervised cross-lingual speaker adaptation}, projects = {Idiap, EMIME}, month = {3}, title = {A Comparison of Supervised and Unsupervised Cross-Lingual Speaker Adaptation Approaches for HMM-Based Speech Synthesis}, booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = {2010}, location = {Dallas, U.S.A.}, crossref = {Liang_Idiap-RR-05-2010}, abstract = {The EMIME project aims to build a personalized speech-to-speech translator, such that spoken input of a user in one language is used to produce spoken output that still sounds like the user's voice however in another language. This distinctiveness makes unsupervised cross-lingual speaker adaptation one key to the project's success. So far, research has been conducted into unsupervised and cross-lingual cases separately by means of decision tree marginalization and HMM state mapping respectively. In this paper we combine the two techniques to perform unsupervised cross-lingual speaker adaptation. The performance of eight speaker adaptation systems (supervised vs. unsupervised, intra-lingual vs. cross-lingual) are compared using objective and subjective evaluations. Experimental results show the performance of unsupervised cross-lingual speaker adaptation is comparable to that of the supervised case in terms of spectrum adaptation in the EMIME scenario, even though automatically obtained transcriptions have a very high phoneme error rate.}, pdf = {https://publications.idiap.ch/attachments/papers/2009/Liang_ICASSP_2010.pdf} }