The Science of Harmony: A Universal Theory

Paul Yaozhu Chan, Minghui Dong and Haizhou Li, 

in Research, vol. 2019, Article ID 2369041, 22 pages, 2019. 

https://spj.sciencemag.org/research/aip/2369041/

 

PiRhDy: Learning Pitch-, Rhythm-, and Dynamics-aware Embeddings for Symbolic Music 

Hongru Liang, Wenqiang Lei, Paul Yaozhu Chan, Zhenglu Yang, Maosong Sun and Tat-Seng Chua,  

in Proceedings - 28th ACM International Conference on Multimedia, 2020.

(Best Paper Award 1 of 1600 submissions)

​

SERAPHIM: A Wavetable Synthesis System with 3D Lip Animation for Real-Time Speech and Singing Applications on Mobile Platforms

Paul Yaozhu Chan, Minghui Dong, Grace X. H. Ho, and Haizhou Li, 

in INTERSPEECH, pp. 1225-1229, 2016.

​

SERAPHIM Live! Singing Synthesis for the Performer, the Composer, and the 3D Game Developer

Paul Yaozhu Chan, Minghui Dong, Grace X. H. Ho, and Haizhou Li, 

in INTERSPEECH, pp. 1966-1967, 2016. 

​

A Wavetable Synthesis System with 3D Lip Animation for Real-time Speech and Singing Applications on Mobile Platforms

Paul Yaozhu Chan, Minghui Dong, Haizhou Li, 

Technical Disclosure. SG/P/2016002, Filed 2016. 

 

Auto-Synchronous Singing Harmonizer

Paul Yaozhu Chan, Minghui Dong, Ling Cen and Siu Wa Lee, 

US Patent, Pub no. US20120234158 A1, App no. US 13/418,236, Published 20 Sep 2012, Filed 12 Mar 2012. 

 

Harmony Synthesizer and Method for Harmonizing Vocal Signals

Paul Yaozhu Chan, Minghui Dong, Ling Cen and Siu Wa Lee, 

PRC Patent, Pub no. CN102682762 A, App no. CN 201210068847, Published 19 Sep 2012, Filed 15 Mar 2012. 

 

Solo to A Capella Conversion - Synthesizing Vocal Harmony from Lead Vocals

Paul Yaozhu Chan, Minghui Dong, Siu Wa Lee, Ling Cen, and Haizhou Li, 

in Proceedings - IEEE International Conference on Multimedia and Expo, 2011. 

(Best Paper Candidate)

​

Template-based Personalized Singing Voice Synthesis

Ling Cen, Minghui Dong and Paul Yaozhu Chan, 

in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 45094512, 2012. 

 

I²R Speech2Singing Perfects Everyones Singing

Minghui Dong, S. W. Lee, Haizhou Li, Paul Chan, Xuejian Peng, Jochen Walter Ehnes, Dongyan Huang, 

in Fifteenth Annual Conference of the International Speech Communication Association, 2012. 

 

Method and System for Template-based Personalized Singing Synthesis

Siu Wa Lee, Ling Cen, Haizhou Li, Paul Yaozhu Chan and Minghui Dong, 

US Patent, App no. 14/383,341, Filed 22 Jan 2015. 

 

Formant Excursion in Singing Synthesis

Paul Yaozhu Chan, Minghui Dong, Yi Qian Lim, Ashleigh Toh, Elliot Chong, Mantita Yeo, Megan Chua and Haizhou Li, 

in Digital Signal Processing (DSP), 2015 IEEE International Conference on., IEEE, 2015. 

 

The Expression of Singing Emotion-Contradicting the Constraints of Song

Gillian Chua, Qian Ci Chang, Ye Won Park, Paul Yaozhu Chan, Minghui Dong, Haizhou Li, 

in Asian Language Processing (IALP), 2015 International Conference on., IEEE, 2015. 

 

Use of Electroglottograph (EGG) to Find a Relationship between Pitch, Emotion and Personality

Hui Lu, Hui Ting Liu, Swee Lan See, Paul Yaozhu Chan, 

in Procedia Manufacturing, 3, 1926-1931, 2015. 

 

The Psychoacoustic Approach towards Enhancing Speech Intelligibility in Noise 

Chan Y.Z. Paul, Dong M.H., Cen Ling 

International Symposium Chinese Spoken Language Processing, (Tainan, ) EI / SCI Published Nov 2010 

 

Readability Consideration in Speech Synthesis Recording Script Selection 

Dong M.H., Cen Ling, Chan Y.Z. Paul 

Journal Chinese Oriental Language and Computing Published Mar 2010

 

Machine Learning Methods in the Application of Speech Emotion Recognition 

Cen Ling, Dong M.H., , Li H.Z., , Yu Z., Chan Y.Z. Paul, 

Application of Machine Learning, IN-TECH     Published Feb 2010

 

Generating Emotional Speech from Neutral Speech 

Cen Ling, Chan Y.Z. Paul, Dong M.H. 

International Symposium on Chinese Spoken Language Processing, (Taiwan, ) EI / SCI   Published Dec 2010

 

Aligning Singing Voice with MIDI Melody Using Synthesized Audio Signal 

Dong M.H. Chan Y.Z. Paul, Cen Ling 

International Symposium Chinese Spoken Language Processing, (Tainan, ) 95-98 EI / SCI  Published Nov 2010

 

Considering Readability in Text-to-Speech Recording Script Design 

Dong M.H. Cen Ling, Chan Y.Z. Paul, Li H.Z. 

ISCA Speech Synthesis Workshop, (Kyoto, ) EI / SCI   Published Sep 2010

 

Phonetic Segmentation of Singing Voice using MIDI and Parallel Speech 

Dong M.H., Chan Y.Z. Paul, Cen Ling, Li H.Z., Teo Z.T.J., Kua P.J. 

Interspeech / International Conference on Spoken Language Processing, EI / SCI   Published Sep 2010

 

Voice Conversion: From Spoken Vowels To Singing Vowels 

Nwe T.L. , Dong M.H., Chan Y.Z. Paul, Wang X., , Ma B., 

IEEE International Conference Multimedia and Expo, (Singapore, ) EI / SCI   Published Jul 2010

 

Refining Unit Boundaries for Mandarin Text-to-Speech Database 

Dong M.H., Cen Ling, Chan Y.Z. Paul 

International Conference Asian Language Processing, (Singapore) EI / SCI   Published Dec 2009

 

I²R Text-to-Speech System for Blizzard Challenge 2009 

Dong M.H., Cen Ling, Chan Y.Z. Paul, Huang D.Y., Zhu D.L., Ma B. 

Blizzard Challenge Workshop, (Edinburgh) Others  Published Sep 2009

 

Unit Selection based Speech Synthesis for Poor Channel Condition

Cen Ling, Dong M.H., Chan Y.Z. Paul 

Interspeech / International Conference on Spoken Language Processing, (Brighton) EI / SCI   Published Sep 2009 

 

Boundary labeling of prosody words for Mandarin TTS database 

Cen Ling, Dong M.H., Chan Y.Z. Paul, Li H.Z. 

International Symposium Asian Speech Resources, (Xinjiang, ) Others   Published Aug 2009