Data-driven emotion conversion in spoken English
Z Inanoglu, S Young - Speech Communication, 2009 - Elsevier
This paper describes an emotion conversion system that combines independent parameter
transformation techniques to endow a neutral utterance with a desired target emotion. A set …
transformation techniques to endow a neutral utterance with a desired target emotion. A set …
A review of paralinguistic information processing for natural speech communication
Y Yamashita - Acoustical Science and Technology, 2013 - jstage.jst.go.jp
Speech conveys not only linguistic information but also supplemental information that is not
inferable from written language, such as attitude, speaking style, intention, emotion, mental …
inferable from written language, such as attitude, speaking style, intention, emotion, mental …
Evaluation of expressive speech synthesis with voice conversion and copy resynthesis techniques
O Turk, M Schroder - IEEE Transactions on Audio, Speech, and …, 2010 - ieeexplore.ieee.org
Generating expressive synthetic voices requires carefully designed databases that contain
sufficient amount of expressive speech material. This paper investigates voice conversion …
sufficient amount of expressive speech material. This paper investigates voice conversion …
Analysis of linguistic and prosodic features of bilingual Arabic–English speakers for speech emotion recognition
L Abdel-Hamid, NH Shaker, I Emara - Ieee Access, 2020 - ieeexplore.ieee.org
Speech emotion recognition (SER) research has usually focused on the analysis of the
native language of speakers, most commonly, targeting European and Asian languages. In …
native language of speakers, most commonly, targeting European and Asian languages. In …
[图书][B] Handling emotions in human-computer dialogues
J Pittermann, A Pittermann, W Minker - 2010 - Springer
During the past years the “mystery” of emotions has increasingly attracted interest in
research on human–computer interaction. In this work we investigate the problem of how to …
research on human–computer interaction. In this work we investigate the problem of how to …
[PDF][PDF] A system for transforming the emotion in speech: combining data-driven conversion techniques for prosody and voice quality.
Z Inanoglu, SJ Young - INTERSPEECH, 2007 - svr-www.eng.cam.ac.uk
This paper describes a system that combines independent transformation techniques to
endow a neutral utterance with some required target emotion. The system consists of three …
endow a neutral utterance with some required target emotion. The system consists of three …
A cloud robotics approach towards dialogue-oriented robot speech
Robot utterances generally sound monotonous, unnatural and unfriendly because their Text-
to-Speech systems are not optimized for communication but for text reading. Here, we …
to-Speech systems are not optimized for communication but for text reading. Here, we …
System and method for singing synthesis capable of reflecting voice timbre changes
2013-01-17 Assigned to NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE
AND TECHNOLOGY reassignment NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL …
AND TECHNOLOGY reassignment NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL …
An intuitive style control technique in HMM-based expressive speech synthesis using subjective style intensity and multiple-regression global variance model
T Nose, T Kobayashi - Speech Communication, 2013 - Elsevier
To control intuitively the intensities of emotional expressions and speaking styles for
synthetic speech, we introduce subjective style intensities and multiple-regression global …
synthetic speech, we introduce subjective style intensities and multiple-regression global …
Synthesis of F0 contours using generation process model parameters predicted from unlabeled corpora: Application to emotional speech synthesis
K Hirose, K Sato, Y Asano, N Minematsu - Speech communication, 2005 - Elsevier
A corpus-based method of generating fundamental frequency (F0) contours from text was
developed for Japanese. Instead of directly predicting F0 values, the method predicts …
developed for Japanese. Instead of directly predicting F0 values, the method predicts …