Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training

IEEE/ACM Transactions on Audio Speech and Language Processing ◽

10.1109/taslp.2016.2551865 ◽

2016 ◽

Vol 24 (7) ◽

pp. 1255-1265 ◽

Author(s):

Zhizheng Wu ◽

Simon King

Keyword(s):

Speech Synthesis ◽

Error Training ◽

Trajectory Modelling

Download Full-text

Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition

Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning ◽

10.1145/3372806.3372819 ◽

2019 ◽

Author(s):

Naoto Umezaki ◽

Takumi Okubo ◽

Hideyuki Watanabe ◽

Shigeru Katagiri ◽

Miho Ohsaki

Keyword(s):

Speech Recognition ◽

Speech Synthesis ◽

Classification Error ◽

Error Training ◽

Minimum Classification Error ◽

Minimum Classification Error Training

Download Full-text

Speech Synthesis for Error Training Models in CALL

Computer Processing of Oriental Languages. Language Technology for the Knowledge-based Economy - Lecture Notes in Computer Science ◽

10.1007/978-3-642-00831-3_24 ◽

2009 ◽

pp. 260-269

Author(s):

Xin Zhang ◽

Qin Lu ◽

Jiping Wan ◽

Guangguang Ma ◽

Tin Shing Chiu ◽

...

Keyword(s):

Speech Synthesis ◽

Training Models ◽

Download Full-text

Minimum Generation Error Training for HMM-Based Speech Synthesis

2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings ◽

10.1109/icassp.2006.1659964 ◽

2006 ◽

Author(s):

Yi-Jian Wu ◽

Ren-Hua Wang

Keyword(s):

Speech Synthesis ◽

Download Full-text

Towards minimum perceptual error training for DNN-based speech synthesis

10.21437/interspeech.2015-268 ◽

2015 ◽

Author(s):

Cassia Valentini-Botinhao ◽

Zhizheng Wu ◽

Simon King

Keyword(s):

Speech Synthesis ◽

Perceptual Error ◽

Download Full-text

Minimum generation error training with weighted Euclidean distance on LSP for HMM-based speech synthesis

2010 IEEE International Conference on Acoustics, Speech and Signal Processing ◽

10.1109/icassp.2010.5495688 ◽

2010 ◽

Author(s):

Ming Lei ◽

Zhen-Hua Ling ◽

Li-Rong Dai

Keyword(s):

Speech Synthesis ◽

Euclidean Distance ◽

Download Full-text

Modulation spectrum-constrained trajectory error training for mixture density network-based speech synthesis

The Journal of the Acoustical Society of America ◽

10.1121/1.5052206 ◽

2018 ◽

Vol 144 (3) ◽

pp. EL151-EL157 ◽

Author(s):

Sangjun Park ◽

Minsoo Hahn

Keyword(s):

Speech Synthesis ◽

Trajectory Error ◽

Modulation Spectrum ◽

Mixture Density ◽

Download Full-text

Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis

10.21437/interspeech.2008-170 ◽

2008 ◽

Author(s):

Yi-Jian Wu ◽

Keiichi Tokuda

Keyword(s):

Speech Synthesis ◽

Spectral Distortion ◽

Download Full-text

A generation error function considering dynamic properties of speech parameters for minimum generation error training for hidden Markov model-based speech synthesis

Acoustical Science and Technology ◽

10.1250/ast.34.123 ◽

2013 ◽

Vol 34 (2) ◽

pp. 123-132

Author(s):

Duy Khanh Ninh ◽

Masanori Morise ◽

Yoichi Yamashita

Keyword(s):

Markov Model ◽

Hidden Markov Model ◽

Speech Synthesis ◽

Hidden Markov ◽

Dynamic Properties ◽

Error Function ◽

Model Based ◽

Download Full-text

Preserve ordering property of generated LSPS for minimum generation error training in HMM-based speech synthesis

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp.2011.5947407 ◽

2011 ◽

Author(s):

Ming Lei ◽

Zhen-Hua Ling ◽

Li-Rong Dai

Keyword(s):

Speech Synthesis ◽

Download Full-text

Incorporating dynamic features into minimum generation error training for HMM-based speech synthesis

2012 8th International Symposium on Chinese Spoken Language Processing ◽

10.1109/iscslp.2012.6423486 ◽

2012 ◽

Author(s):

Duy Khanh Ninh ◽

Masanori Morise ◽

Yoichi Yamashita

Keyword(s):

Speech Synthesis ◽

Dynamic Features ◽

Download Full-text