Using eigenvoices and nearest-neighbors in HMM-based cross-lingual speaker adaptation with limited data

Name: Using eigenvoices and nearest-neighbors in HMM-based cross-lingual speaker adaptation with limited data
Author: Sarfjoo, Seyyed Saeed, Demiroğlu, Cenk, King, S.

İsim	Using eigenvoices and nearest-neighbors in HMM-based cross-lingual speaker adaptation with limited data
Yazar	Sarfjoo, Seyyed Saeed, Demiroğlu, Cenk, King, S.
Basım Tarihi:	2017-04
Basım Yeri	- IEEE
Konu	Cross lingual speaker adaptation, Statistical speech synthesis, Speaker adaptation, Nearest neighbour
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2329-9304
Kayıt Numarası	ee9f3091-c0c9-4a59-92e6-4caaef7adf64
Lokasyon	Electrical & Electronics Engineering
Tarih	2017-04
Notlar	European Commission ; TUBITAK
Örnek Metin	Cross-lingual speaker adaptation for speech synthesis has many applications, such as use in speech-to-speech translation systems. Here, we focus on cross-lingual adaptation for statistical speech synthesis systems using limited adaptation data. To that end, we propose two eigenvoice adaptation approaches exploiting a bilingual Turkish-English speech database that we collected. In one approach, eigenvoice weights extracted using Turkish adaptation data and Turkish voice models are transformed into the eigenvoice weights for the English voice models using linear regression. Weighting the samples depending on the distance of reference speakers to target speakers during linear regression was found to improve the performance. Moreover, importance weighting the elements of the eigenvectors during regression further improved the performance. The second approach proposed here is speaker-specific state-mapping, which performed significantly better than the baseline state-mapping algorithm both in objective and subjective tests. Performance of the proposed state mapping algorithm was further improved when it was used with the intralingual eigenvoice approach instead of the linear-regression based algorithms used in the baseline system.
DOI	10.1109/TASLP.2017.2667880
Cilt	25

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Using eigenvoices and nearest-neighbors in HMM-based cross-lingual speaker adaptation with limited data

Yazar Sarfjoo, Seyyed Saeed, Demiroğlu, Cenk, King, S.

Basım Tarihi 2017-04

Basım Yeri - IEEE

Konu Cross lingual speaker adaptation, Statistical speech synthesis, Speaker adaptation, Nearest neighbour

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2329-9304

Kayıt Numarası ee9f3091-c0c9-4a59-92e6-4caaef7adf64

Lokasyon Electrical & Electronics Engineering

Tarih 2017-04

Notlar European Commission ; TUBITAK

Örnek Metin Cross-lingual speaker adaptation for speech synthesis has many applications, such as use in speech-to-speech translation systems. Here, we focus on cross-lingual adaptation for statistical speech synthesis systems using limited adaptation data. To that end, we propose two eigenvoice adaptation approaches exploiting a bilingual Turkish-English speech database that we collected. In one approach, eigenvoice weights extracted using Turkish adaptation data and Turkish voice models are transformed into the eigenvoice weights for the English voice models using linear regression. Weighting the samples depending on the distance of reference speakers to target speakers during linear regression was found to improve the performance. Moreover, importance weighting the elements of the eigenvectors during regression further improved the performance. The second approach proposed here is speaker-specific state-mapping, which performed significantly better than the baseline state-mapping algorithm both in objective and subjective tests. Performance of the proposed state mapping algorithm was further improved when it was used with the intralingual eigenvoice approach instead of the linear-regression based algorithms used in the baseline system.

DOI 10.1109/TASLP.2017.2667880

Cilt 25