Unsupervised speaker adaptation for speaker independent acoustic to articulatory speech inversion
Speech inversion is a well-known ill-posed problem and addition of speaker differences typically makes it even harder. Normalizing the speaker differences is essential to effectively using multi-speaker articulatory data for training a speaker independent speech inversion system. This paper explores...
Main Authors: | Espy-Wilson, C. (Author), Mitra, V. (Author), Nam, H. (Author), Sivaraman, G. (Author), Tiede, M. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Acoustical Society of America
2019
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
From Acoustics to Articulation : Study of the acoustic-articulatory relationship along with methods to normalize and adapt to variations in production across different speakers
by: Ananthakrishnan, Gopal
Published: (2011) -
Automatic Speaker Recognition Dependency on Both the Shape of Auditory Critical Bands and Speaker Discriminative MFCCs
by: JOKIC, I., et al.
Published: (2015-11-01) -
A Tutorial on Text-Independent Speaker Verification
by: Frédéric Bimbot, et al.
Published: (2004-04-01) -
Automatic Speaker Recognition Based on Mel-Frequency Cepstral Coefficients and Gaussian Mixture Models
by: Sheeraz Memon, et al.
Published: (2013-10-01) -
Text-Independent Speaker Identification Using the Histogram Transform Model
by: Zhanyu Ma, et al.
Published: (2016-01-01)