Non-parallel training for many-to-many eigenvoice conversion

Ohtani, Yamato; Toda, Tomoki; Saruwatari, Hiroshi; Shikano, Kiyohiro

doi:10.1109/icassp.2010.5495139

Cited by 16 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this challenge, the proposed training algorithm of IC-GMR should be extended to the case of non-parallel corpus as considered in [35]. Moreover, the use of the C-GMR framework (and notably the IC-GMR approach) could be envisioned in other speech processing areas, such as silent speech interfaces [36] which are devices converting speech-related biosignals (e.g.…”

Section: Discussionmentioning

confidence: 99%

Speaker-Adaptive Acoustic-Articulatory Inversion Using Cascaded Gaussian Mixture Regression

Hueber

Girin

Alameda-Pineda

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

This article addresses the adaptation of an acoustic-articulatory model of a reference speaker to the voice of another speaker, using a limited amount of audio-only data. In the context of pronunciation training, a virtual talking head displaying the internal speech articulators (e.g. the tongue) could be automatically animated by means of such a model using only the speaker's voice. In this study, the articulatory-acoustic relationship of the reference speaker is modeled by a gaussian mixture model (GMM). To address the speaker adaptation problem, we propose a new framework called cascaded Gaussian mixture regression (C-GMR), and derive two implementations. The first one, referred to as Split-C-GMR, is a straightforward chaining of two distinct GMRs: one mapping the acoustic features of the source speaker into the acoustic space of the reference speaker, and the other estimating the articulatory trajectories with the reference model. In the second implementation, referred to as Integrated-C-GMR, the two mapping steps are tied together in a single probabilistic model. For this latter model, we present the full derivation of the exact EM training algorithm, that explicitly exploits the missing data methodology of machine learning. Other adaptation schemes based on maximum-a-posteriori (MAP), maximum likelihood linear regression (MLLR) and direct crossspeaker acoustic-to-articulatory GMR are also investigated. Experiments conducted on two speakers for different amount of adaptation data show the interest of the proposed C-GMR techniques.

show abstract

Section: Discussionmentioning

confidence: 99%

Speaker-Adaptive Acoustic-Articulatory Inversion Using Cascaded Gaussian Mixture Regression

Hueber

Girin

Alameda-Pineda

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…VC-EVC: A many-to-many eigenvoice conversion (EVC) system [54]. The eigenvoice GMM (EV-GMM) is constructed from the training data of one pivot speaker in the ATR Japanese speech database [55], and 273 speakers (137 male, 136 female) from the JNAS database 11 .…”

Section: A Spoofing Systemsmentioning

confidence: 99%

Anti-Spoofing for Text-Independent Speaker Verification: An Initial Database, Comparison of Countermeasures, and Human Performance

León

Demiroğlu

et al. 2016

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

In this paper, we present a systematic study of the vulnerability of automatic speaker verification to a diverse range of spoofing attacks. We start with a thorough analysis of the spoofing effects of five speech synthesis and eight voice conversion systems, and the vulnerability of three speaker verification systems under those attacks. We then introduce a number of countermeasures to prevent spoofing attacks from both known and unknown attackers. Known attackers are spoofing systems whose output was used to train the countermeasures, whilst an unknown attacker is a spoofing system whose output was not available to the countermeasures during training. Finally, we benchmark automatic systems against human performance on both speaker verification and spoofing detection tasks.

show abstract

“…VC-EVC: This is a many-to-many eigenvoice conversion (EVC) system [34]. The eigenvoice GMM (EV-GMM) was constructed from the training data from one pivot speaker in the ATR Japanese speech database [35], and 273 speakers (137 male, 136 female) from the JNAS database.…”

Section: Ss-largementioning

confidence: 99%

SAS: A speaker verification spoofing database containing diverse attacks

Khodabakhsh

Demiroğlu

et al. 2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

This paper presents the first version of a speaker verification spoofing and anti-spoofing database, named SAS corpus. The corpus includes nine spoofing techniques, two of which are speech synthesis, and seven are voice conversion. We design two protocols, one for standard speaker verification evaluation, and the other for producing spoofing materials. Hence, they allow the speech synthesis community to produce spoofing materials incrementally without knowledge of speaker verification spoofing and anti-spoofing. To provide a set of preliminary results, we conducted speaker verification experiments using two state-of-the-art systems. Without any anti-spoofing techniques, the two systems are extremely vulnerable to the spoofing attacks implemented in our SAS corpus.

show abstract

Non-parallel training for many-to-many eigenvoice conversion

Cited by 16 publications

References 12 publications

Speaker-Adaptive Acoustic-Articulatory Inversion Using Cascaded Gaussian Mixture Regression

Speaker-Adaptive Acoustic-Articulatory Inversion Using Cascaded Gaussian Mixture Regression

Anti-Spoofing for Text-Independent Speaker Verification: An Initial Database, Comparison of Countermeasures, and Human Performance

SAS: A speaker verification spoofing database containing diverse attacks

Contact Info

Product

Resources

About