Iterative MMSE Estimation of Vocal Tract Length Normalization Factors for Voice Transformation

被引：0

作者：

Erro, Daniel ^{[1
]}

Navas, Eva ^{[1
]}

Hernaez, Inma ^{[1
]}

机构：

[1] Univ Basque Country UPV EHU, AHOLAB, Bilbao, Spain

来源：

13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3 | 2012年

关键词：

vocal tract length normalization; voice conversion; frequency warping plus amplitude scaling; speech synthesis;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a method that determines the optimal configuration of a bilinear vocal tract length normalization function to transform the frequency axis of one voice according to a specific target voice. Given a number of parallel utterances of the involved speakers, the single parameter of this function can be calculated through an iterative procedure by minimizing an objective error measure defined in the cepstral domain. This method is also applicable when multiple warping classes are considered, and it can be complemented with amplitude correction filters. The resulting physically motivated cepstral transformation results in highly satisfactory conversion accuracy and improved quality with respect to standard satistical systems.

引用

页码：86 / 89

页数：4

共 50 条

[41] On Short-Time Estimation of Vocal Tract Length from Formant Frequencies
Lammert, Adam C.
Narayanan, Shrikanth S.
[J]. PLOS ONE, 2015, 10 (07):
[42] Unsupervised estimation of the human vocal tract length over sentence level utterances
Necioglu, BF
Clements, MA
Barnwell, TP
[J]. 2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 1319 - 1322
[43] A novel approach to the estimation of voice source and vocal tract parameters from speech signals
Ding, W
Kasuya, H
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1257 - 1260
[44] SIMULTANEOUS ESTIMATION OF VOCAL-TRACT AND VOICE SOURCE PARAMETERS BASED ON AN ARX MODEL
DING, W
KASUYA, H
ADACHI, S
[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1995, E78D (06) : 738 - 743
[45] Unsupervised Vocal Tract Length Warped Posterior Features for Non-Parallel Voice Conversion
Shah, Nirmesh J.
Madhavi, Maulik C.
Patil, Hemant A.
[J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1968 - 1972
[46] Effects of speaker normalization based on vocal tract length ratios on word recognition using compound parameters
[J]. Ikeda, N, 1600, John Wiley and Sons Inc. (36):
[47] Feature compensation based on the normalization of vocal tract length for the improvement of emotion-affected speech recognition
Geravanchizadeh, Masoud
Forouhandeh, Elnaz
Bashirpour, Meysam
[J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2021, 2021 (01)
[48] Feature compensation based on the normalization of vocal tract length for the improvement of emotion-affected speech recognition
Masoud Geravanchizadeh
Elnaz Forouhandeh
Meysam Bashirpour
[J]. EURASIP Journal on Audio, Speech, and Music Processing, 2021
[49] A preliminary study of voice quality transformation based on modifications to the neutral vocal tract area function
Story, BH
Titze, IR
[J]. JOURNAL OF PHONETICS, 2002, 30 (03) : 485 - 509
[50] Mixed source model and its adapted vocal tract filter estimate for voice transformation and synthesis
Degottex, Gilles
Lanchantin, Pierre
Roebel, Axel
Rodet, Xavier
[J]. SPEECH COMMUNICATION, 2013, 55 (02) : 278 - 294

← 1 2 3 4 5 →