Emotional speech synthesis: a review

By Marc Schröder. Interspeech, 2001

436 citations recorded by the source corpus.

Attempts to add emotion effects to synthesised speech have existed for more than a decade now. Several prototypes and fully operational systems have been built based on different synthesis techniques, and quite a number of smaller studies have been conducted. This paper aims to give an overview of what has been done in this field, pointing out the inherent properties of the various synthesis techniques used, summarising the prosody rules employed, and taking a look at the evaluation paradigms. Finally, an attempt is made to discuss interesting directions for future development.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Social Psychology

View Paper: https://www.semanticscholar.org/paper/fede6fe5b167164039762ef44840210dddba991c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Experimental and Cognitive Psychology

In Social Psychology

Citations in the corpus

Creating Interactive Virtual Humans: Some Assembly Required (2002, neutral): “25 While the interest in affective speech synthesis is increasing, hardly any work has been done on conveying emotion through sentence structure or word choice.”
Emotion representation, analysis and synthesis in continuous space: A survey (2011, background): “research area [89], [90], [91] with a major focus on discrete representation of basic emotions.”
The New Handbook of Methods in Nonverbal Behavior Research (2008, methodology): “There are, broadly speaking, three diVerent approaches to synthesis (Schröder 2001).”
Communication of emotions in vocal expression and music performance: different channels, same code? (2003, methodology): “This method makes it possible to manipulate certain cues of an emotion portrayal while leaving other cues intact (e.g., Juslin & Madison, 1999; Ladd et al., 1985; Schröder, 2001).”
Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “of TTS techniques from the formant-based methods [92, 97, 105, 106, 179, 224] to the unit selection-based waveform cascade methods [6, 24, 36, 59, 80, 143, 144], and to the hidden Markov model (HMM)-based statistical parametric speech synthesis (SPSS) methods [26, 94, 149, 178, 210, 241, 249, 250].”
Unsupervised Learning for Expressive Speech Synthesis (2017, methodology): “In some works, as by Schuller (2000); Lopez-Otero et al.”
Semi-Supervised Generative Modeling for Controllable Speech Synthesis (2019, background): “• To demonstrate that as little as 30 minutes supervision can be sufﬁcient to improve prosody and allow control over speaking rate, fundamental frequency (F0) variation and affect, a problem of interest to the speech community for well over two decades (Schr ¨ oder, 2001).”
Emotion recognition from speech: a review (2012, background): “Purpose of sophisticated speech systems should not be limited to mere message processing, rather they should understand the underlying intentions of the speaker by detecting expressions in speech (Schroder 2001; Ververidis and Kotropoulos 2006).”
Speech Synthesis Based on Hidden Markov Models (2013, background): “Expressive Speech Synthesis Similar to the naturalness of synthesized speech, expression of emotion is one of the important issues which should be considered [72].”