site navigation

Expressive Synthetic Speech

(pictures taken from Paul Ekman )

last update: March 24th 2025

This is a collection of examples of synthetic affective speech conveying an emotion or natural expression and maintained by Felix Burkhardt. Some of these samples are direct copies from natural data, others are generated by expert-rules or derived from data-bases. The emotional labels "anger", "fear", "joy" and "sad" are my (short) designators for "the big four" basic emotions, not neccessarily the authors' ones.
Examples of German actors simulating emotional arousal can be found here.
I recently held a talk on emotional speech synthesis.
Examples of German text-to-speech synthesizers can be found here.
Please, feel encouraged to let me know about own or missing attempts to simulate emotional speech! (fxburk@gmail.com)

contents

• comparing simulation of anger, fear, joy and sadness
• other simulations
• related examples
• end2end deep learning examples
• missing examples
• further links
• projects concerning emotional speech
• changelog

All Audiofiles are Mp3-format (128 or 64 kB/s)

author	visual	affil.	year (approx)	description	neutral	anger	joy	sad	fear
N. Audibert, V. Aubergé, A. Rilliard		ICP	2006	Copy prosody and intensity from satisfied and sad speech to neutral speech using PSOLA technique. See the article "The Prosodic Dimensions of Emotion in Speech: the Relative Weights of Parameters", Interspeech 2005 (Lisbon), for details		-			-
Stephan Baldes		DFKI	1999	Rule based emotion simulation with Entropic's formant TTS engine TrueTalk, based on Cahn's affect editor approach	-		-
Roberto Barra Chicote		Polytechnic Univ. of Madrid	2010	HMM based emotional speech synthesis, i.e. used emotional prosodic and source models on HMM coded speech data. See the article "Roberto Barra-Chicote, Junichi Yamagishi, Simon King, Juan Manuel Montero, Javier Macias-Guarasa, Analysis of statistical parametric and unit selection speech synthesis systems applied to emotional speech, Speech Communication, Volume 52, Issue 5,2010".for details.
Murtaza Bulut, Carlos Busso, Serdar Yildirim, Abe Kazemzadeh, Chul Min Lee, Sungbok Lee, Shrikanth Narayanan		USC/Sail	2005	Emotional voice-conversion by changing prosody (TD-PSOLA) and spectrum (LPC modification). The samples demonstrate neutral to target-emotion conversion. See the article "Investigating the role of phoneme-level modifications in emotional speech resynthesis", Proc Interspeech 2005 for details					-
Murtaza Bulut, Shri Narayanan, Ann Syrdal		USC/Sail, AT&T	2002	Diphone synthesis done with hand-crafted diphones and copy-prosody for the appropriate emotion. See the article "Expressive Speech Synthesis Using a Concatenative Synthesizer", Proc. ICSLP 2002, for details					-
Felix Burkhardt		Dautsche Telekom Laboratories	2005	emofilt: rule based simulation (prosody only) with MBROLA. German male voice (de6) (neutral prosody txt2pho)
				English male voice (en1)
				Spanish male voice (es2)
				Mandarin Chinese female voice (cn1)
				Frensh male voice (fr1)
				Greek male voice (gr2)
				Dutch male voice (nl2)
				Hungarian male voice (hu1)
				Italian male voice (it3)
				Turkish male voice (tr1)
			1998	emofilt old version
			2000	emoSyn 1: rule based simulation with formant-synthesizer (Sensyn Version), the neutral sentence is copy-synthesis, more examples here
			2000	emoSyn 2: copy synthesis with formant-synthesizer (Iles & Simmons Version)	orig.
					synth.
			1998	esps2mbrola: prosody-copy synthesis with MBROLA	orig.
					synth.
Joao P. Cabral		L2F INESC-ID Lisboa	2005	Transformation of neutral speech using LP-PSOLA. Changes pitch, duration and energy as well as voicequality (by transforming the residual). Emotion-rules were derived from literature. See the article "Pitch-Synchronous Time-Scaling for Prosodic and Voice Quality Transformations", Proc. Interspeech 2005 for details. male voice
				female voice
Janet Cahn		MIT	1989 ?	Affect Editor: rule based emotion simulation with DecTalk	-
Piero Cosi, Fabio Tesser, Roberto Gretter, Carlo Drioli, Graziano Tisato		ISTC-SPFD	2004	Emotive Mbrola: Italian concatenation synthesis with the Festival speech synthesis framework and MBROLA voices. The prosody was learned from emotional database (CART). An article appeared at the Interspeech 2005. male voice
				female voice
				with manipulation of voice quality	male voice
					female voice
Cosy Voice		FunAudioLLM	2025	Version 2.0 end-2-end emotional speech synthesis					-
Coqui.ai		Coqui	2023	Ana Florence (one of many voices): Deep learning based latent space synthesis.
Björn Granström, Rolf Carlson ?		KTH	1998 ?	KTH Royal Institute of Technology (orig. link broken): swedish copy formant-synthesis.					-
author	visual	affil.	year (approx)	description	neutral	anger	joy	sad	fear
Akemi Iida		ATR	2000 ?	Chatr Emotion: japanese concatenation synthesis using emotional databases with CHATR. See the article "A Speech Synthesis System with Emotion for Assisting Communication", Proc. ISCA Workshop on Speech and Emotion, Belfast, 2000. Since than Chatr has been expanded to NATR	-				-
				new CHATR with Emotion	-				-
David from IRCAM		IRCAM	2015	Not a speech synthesizer, but re-synthesis to "emotionalize" existing speech by pitch-shifting, filtering, adding vibrato and inflections, see the article "DAVID: An open-source platform for real-time transformation of infra-segmental emotional cues in running speech" , Behaviour Research Methods (2017) for details		-
Gregor Hofer		Univ. Edinburgh	2004	Gregor Hofer's master's thesis, unit selection database recorded in neutral as well as happy and angry style. More samples.				-	-
					half-emotional by mixing units from neutral and emotional data			-	-
Ignasi Iriondo, Francesc Alías, Javier Melenchón, M. Angeles Llorca		Univ. Ramon Lull	2003	Catalan diphone synthesis with emotion rules, see article "Modeling and Synthesizing Emotional Speech for Catalan Text-to-Speech Synthesis" (Proc. ADS 2004) for details	-
Syaheerah L. Lutfi		Polytechnic Univ. of Madrid	2006	Template/rule-based synthesis of prosody parameters using Mbrola synthesis, see the article "Syaheerah L. Lutfi, Raja N. Ainon and Zuraidah M. Don. eXpressive Text Reader Automation Layer (eXTRA): Template driven ‘Emotion Layer’ in Malay Concatenated Synthesized Speech, Proc. of International Conference on Speech Databases and Assessment (Oriental COCOSDA 06), Penang, Malaysia, Dec 2006" for details.			-	-	-
Cynthia Breazeal		MIT	2000	Kismet: rule based emotion simulation with DecTalk (like Affect Editor)
				with words
Keisuke Miyanaga, Makoto Tachibana, Junichi Yamagishi, Koji Onishi, Takashi Masuko, Takao Kobayashi		Tokyo Institute of technology, Kobayashi Lab.	2004	HMM (data-based) modeling of emotional expression (spectral and prosodic), enables mixing: see article HMM-Based Speech Synthesis with Various Speaking Styles Using Model Interpolation or further demos: each emotion individually modeled					-
				emotion as contextual factor (like phonetic/linguistic factors)					-
Juan M. Montero Martínez		Univ. Madrid	1998 ?	montero 1: rule based emotion simulation with spanish diphone-synthesizer					-
				montero 2: rule based emotion simulation with KTH-formant-synthesizer					-
Shinya Mori, Tsuyoshi Moriyama, Shinji Ozawa		Dept. of Media and Image Technology, Tokyo Polytechnic University	2008	PSOLA transformation based on data-base trained prosody modification rules. The algorithm includes possibility of graded expressions. See the article "Emotional Speech Synthesis Using Subspace Constraints in Prosody", Proc. ICME 2006, or follow this link	half				-
					full				-
Iain Murray		Univ. Dundee	1989 ?	HAMLET: rule-based simulated emotions with formant speech synthesis
			1997	Laureate: hand optimized concatenation tts
			1997	LAERTES: rule-based simulation using laureate
Pierre-yves Oudeyer		Sony	2000	cartoon speech: nonsense speech for sony pet-robots based on concatenative synthesis. Article: Oudeyer P-Y. "The Synthesis of Cartoon Emotional Speech", Proc. of the 1st International Conference on Prosody, Aix-en-Provence, eds. B. Bel; I. Marlien. 2002	low intensity				-
					high intensity				-
					with japanese words				-
?		IBM Tokyo Research Laboratory	1996	ProTalker, from IBM tokyo research laboratory.				-	-
S. R. M. Prasanna and D. Govind		Indian Institute of Technology Guwahati	2010	Modeling pitch and excitation (voice source and EGG estimated with the zero frequency filtering approach) with linear prediction using the EMO-DB. See the article "Analysis of Excitation Source Information in Emotional Speech" from Interspeech 2010, Makuhari, for details.	-			-
Erhard Rank/Hannes Pirker		ÖFAI	1998	VieCtoS: demos of the demisyllable LPC-synthesizer VieCtoS of the Austrian Research Institute for Artificial Intelligence (ÖFAI) copying emotional speech
Marc Schröder		DFKI	2002	While working on the NECA-Project and his ph.d. thesis Marc developed a system capable of producing emotional speech based on a description from emotional dimensions (arousal, valence, potency). I tried to map his results to basic emotions. The system is based on MBROLA as DSP and MARY as NLP. In order to control voice-quality, six databases for MBROLA were developed: For male and female each normal, tense voice and lax voice.	-
Ingmar Steiner and Marc Schröder, and Marcela Charfuelan		Mary DFKI Pavoque project	2011	Non-uniform unit selection with a database annotated with expressive styles, see the article "Steiner, Ingmar, Marc Schröder, Marcela Charfuelan (2010) "Symbolic vs. acoustics-based style control for expressive unit selection" 7th ISCA Workshop on Speech Synthesis, Kyoto, Japan", for details.					-
Jun Sato		?	1998 ?	Japanese demo of emotional synthetic speech generated by art. neural nets. Article: J. Sato and S. Morishima, "Emotion modeling in speech production using emotion space", in Proc. IEEE Int. Workshop on Robot and Human Communication, Tsukuba, Japan, Nov. 1996					-
Oytun Türk and Marc Schröder		DFKI	2008	GMM based voice conversion, i.e. the spectral envelope of neutral speech gets transfered to the target emotional speech in order to simulate emotional voice quality without having to record a whole emotional database. See the article "A Comparison of Voice Conversion Methods for Transforming Voice Quality in Emotional Speech Synthesis", Proc. Interspeech 2008, Brisbane.	orig.				-
					synth. (GMM method)				-
E. Zovato, A. Pacchiotti, S. Quazza, S. Sandri		Loquendo	2004	From Loquendo. Rule-based prosody PSOLA-like manipulation of non-uniform unit-selection engine, see Towards emotional speech synthesis: a rule based approach. Presented at the 5th ISCA Workshop on Speech Synthesis in Pittsburgh 2004. other examples from Loqendo					-
Kun Zhou		National University of Singapore	2023	Deep learning approach, actually featuring mixed emotions, see the paper Speech Synthesis with Mixed Emotions	-				-
Yuexin Cao		Ping An Technology	2020	Deep learning approach, combining VAEs with GANS, the actual emotion labels used for the conversion is supervised. See the paper Nonparallel Emotional Speech Conversion Using VAE-GAN					-

Speech Synthesis with Mixed Emotions

examples not simulating the "big four"

author	visual	affil.	year (approx)	description	samples
Acapela		Acapela	2013	Non uniform unit selection synthesis with different emotional and style-varying voices. UK English Voice	Elizabeth Peter neutral Peter happy Peter sad
			2013	Non uniform unit selection synthesis with different emotional and style-varying voices. French Voice	Antoine neutral Antoine happy Antoine sad Antoine from afar Antoine up close
			2013	Non uniform unit selection synthesis with different emotional and style-varying voices. US English Voice	Will neutral Will happy Will sad Will bad guy Will from afar Will up close
Baird, Amiriparian and Schuller		University of Augsburg	2020	WaveNet (deep learning) based approach to generate new emotional speech trained on the Italian DEMoS corpus to enrich the training samples, please see the article for detailes	Simulation of joy Simulation of sadness
Greg Beller		IRCAM	2005	Transform real voices thanks to a content-based transformation with a phase vocoder algorithm. Time-stretch and transpose coefficients change over the utterance depending on the expressivity and the context of units (whether they're part of an accentuated syllable or whether they're consonants, for instance...).	original sad transformation bored transformation frightened transformation
			2009	Synthesis of laughter based on a spring model and the repetition of specific phones. Examples found here	synthesized laughter
?		Cepstral	2004	Non-uniform unit selection. Databases recorded with a certain style.	Damian: dark personality Duchess: sensitive voice Shouty: non-sensitive voice
?		ETI Eloquence (as Eloquent belongs to Scansoft now, the link is broken)	1998	Rule-based formant-syntresis. The emotional expression was hand-optimized (demonstration from Eloquent)	expressive male expressive female
Ellen Eide et al		IBM Watson research Center	2004	Non-uniform unit-selection trained with an expressive prosody model, paralinguistic events and expressive units. Described in the article A Corpus-Based Approach to <AHEM/> Expressive Speech Synthesis	good news bad news question other for comparison: IBM-CTTS taken from website. Note that research-engine is advanced technology compared to product.
Chengyi Wang et al.		Microsoft Vall-e	2023	Neural speech synthesis that takes a text and a short (3 sec) speech sample as input and generates an audio with the textual content in the style and voice of the speech sample	Angry Sleepy Neutral Amused Disgusted human: tts:
IBM Watson		IBM Watson Developer Cloud	2016	Watson voice Allison: Non-uniform unit-selection in three styles: Good News, Apology, and Uncertain	apology uncertain good news
Eva Szekely et al		University College Dublin	2011	HMM synthesis based on expressive Speech extracted automatically from audio textbook readings by clustering Glottal parameters. Described in the article Clustering Expressive Speech Styles in Audiobooks Using Glottal Source Parameters	soft style tense style expressive style
Enrico Zovato et al		Loquendo	2004	Non-uniform unit-selection enriched by paralinguistic events and expressive units. Other examples from Loquendo.	German (Kathrin)/(Stefan) French (Juliette) English (Simon) /
F. Malfrere		MBROLIGN from TCTS Lab, Mons	1999	data-based prosody synthesis with MBROLA (the decision-tree algorithm was trained on a database spoken with the appropriate affect)	neutral nervous astonished shy
Google Deepmind WaveNet		Google Deepmind WaveNet	2016	Synthesis by PCM value prediction from deep neural net. See the paper "WAVENET: A GENERATIVE MODEL FOR RAW AUDIO", by Oord et. al for details. Samples for models trained on three different speakers. Sample for speech without given text, computed by probability from previous samples.	Speaker 1 Speaker 2 Speaker 3 No text given
Kaiser and Schallner		Nuremburg Institute for Market decisions	2020	The system uses a Tacotron (deep learning) based architecture utilizing global Style Tokens (GST) and text-prediction for style embeddings (TPSE) for an emotional speech synthesizer to investigate speech assistants in German, see the paper for a description.	Excited Happy Uninvolved
Ivo-Software		Ivona	2011	Non-uniform Selection Synthesis, Character voice	Chipmunk
John Stallo		Metaface from Curtin University	2000	Implementation of Virtual Human Markup Language, which includes emotional expression. TTS based on Festival and John Stallo's work on "Simulating Emotional Speech for a Talking Head" which implements prosody rules.	happy-cry happy-go-lucky so-afraid
Jürgen Trouvain, Sarah Schmidt, Marc Schröder, William Barry		Personality modeling from Saarland University	2006	Modeling of different personality types with the DFKI Mary system. Modification was done with respect to pitch range and level, speech tempo and voice loudness. See the article "Modelling personality features by changing prosody in synthetic speech", Proc. Speech Prosody 2006, Dresden, for details.	neutral competent excited rugged sincere sophisticated
Meta (facebook)		dGSLM	2022	Generating Chit chat trained form human conversations with (textless) transformer models.	dialog generative spoken language modeling
?		ModelTalker from the University of Delaware	1998	biphone synthesis (biphone-inventory searches for best diphones at synthesis time). The emotional expression was generated by prosody-rules	neutral happy surprised frustrated sad contradictive assertive
Nick Campbell. further samples		NATR from ATR	2004	Non-uniform unit-selection working on a very large database (recording a woman for 3 years) including affective labeling and extralinguistic sounds. See the article "Extra-Semantic Protocols; Input Requirements for the Synthesis of Dialogue Speech" (Proc. ADS 2004) for details.	sample of a telefone conversation between NATR (female voice) and a young man (originally talking to his friend).
?		Rhetorical, now owned by Scansoft. Eduardo	2002	non-uniform unit-selection synthesis done by Rhetorical, character for a Jim Beam marketing campaign, manually optimized	in conversation with rhetorical's voice "american valley girl"
Marc Schröder		DFKI	2002	more examples (see above)	excited scared sad angry 1 angry 2 angry 3 bored content 1 content 2 content 3 happy
MARY		DFKI	2005	Limited domain unit-selection with emotional units.	standard EmotionML sample with Pavoque database from the Mary 5.1 version excited soccer reports
Mariet Theune		Human Media Interaction lab from Univ. Twente	2006	Extracting prosodic rules to enhance speaking style for story tellers and apply to TTS. See the article "Generating Expressive Speech for Storytelling Applications" by Mariet Theune, Koen Meijs, Dirk Heylen and Roeland Ordelman. IEEE Transactions on Audio, Speech and Language Processing 14(4)	no suspense sudden climax increasing climax
Olivier Rosec and Yannis Agiomyrgiannakis		Voice transformation based on an ARX-LF vocoder from Orange Labs, Lannion	2009	Voice transformation based on parameter modification with a combination of LF-excitation and hamrmonic model. See the article: Yannis Agiomyrgiannakis, Olivier Rosec: "ARX-LF-based source-filter methods for voice modification and transformation", Proc. ICASSP 09	man original man whisper man breathy man tense woman original woman as man woman as child
Raul Fernandez and Bhuvana Ramabhadran, IBM TJ Watson research center		Emphatic Speech	2007	Classifying emphatic speech in a non-uniform unit selection database. See the article "Automatic Exploration of Corpus-Specific Properties for Expressive Text-to-Speech." by Raul Fernandez and Bhuvana Ramabhadran. Proc. 6th ISCA workshop on speech synthesis, Bonn, 2007	baseline neutral units with normal text baseline plus collected emphatic units with marked emphasis text mined emphasis corpus with marked emphasis text
Shiva Sundaram and Shrikant Narayanan		SAIL	2007	Synthesis of laughter based on a mass-spring model and LPC synthesis. See the article Sundaram, s. and Narayanan, S., "Automatic acoustic synthesis of human-like laughter", Jasa No1, p. 527-535, 2007.	snythesized laughter
Speechconcept/CereProc		Cerevoice	2009	Non-uniform unit selection synthesis with emotional expression, Courtesy of Speechconcept	Voice Alex Voice Gudrun Voice Nick Voice Saskia
Tacotron		Tacotron with Global Style Tokens	2018	Deep artificial neural nets, described in the paper Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis. In short: so called style tokens are learned from reference samples for a specific speaking style in an unsupervised manner and can then be used as embeddings on a neural net that transforms text to spectrograms. The reference samples or text don't need to be part of the original training and they can be applied to a different degree.	Style 1 Style 2 Style 3 Style 4 Style 5
Talkback		Talkback 2000 (original link broken)	1998	concatenation synthesis, demonstration from Talking Technologies	expressive male expressive female
Tuomo Raitio and Antti Suni		Glott-HMM synthesis	2013	Statistical parametric speech synthesis, the shouted voice was created by adapting the statistical speech models. Part of an analysis-by-synthesis experiment described in the article "Analysis and Synthesis of Shouted Speech" by Tuomo Raitio et al, at Interspeech 2013.	female normal female shouting male normal male shouting
Voxygen		Voxygen	2012	French non-uniform unit-selection, different expressive voices	Voice "Papi" reading an arbitrary news item. Dark Vador Yeti Witch
Yossef Ben-Ezra ?		Vivotext	2012	Technology unknown, demonstration from webpage	happy child sad child

related examples

Lyrebird		Synthesis based on a deep artificial neural net adapted to new speakers voice characteristics (this page's author) from just about 100 short samples
Preserving Word-level Emphasis in Speech-to-speech Translation		Preserving Word-level Emphasis in Speech-to-speech Translation example English to Japanese using Linear Regression HSMMs. As described here or see the Interspeech 2015 article Preserving Word-level Emphasis in Speech-to-speech Translation using Linear Regression HSMMs by Quoc Truong Do, Shinnosuke Takamichi, Sakriani Sakti, Graham Neubig, Tomoki Toda and Satoshi Nakamura	English native speaker Japanese translation without emphasis Japanese translation with emphasis
Accent cloning based on articulatory adaption		Copying accent from a native speaker to a learning non-native speaker by driving an (copysynthesis) articulatory synthesizer for the learner with gestures from the native speaker. As described here or see the Interspeech 2015 article Articulatory-based conversion of foreing accents with deep neural networks by Sandesh Aryal and Ricardo Gutierrez-Osuna	MFCC resinthesized native speaker MFCC resinthesized learning speaker DNN based accent conversion
Voice cloning		A multilinugal speech synthesizer that learned one speaker's voice. From Microsoft research (Frank Soong) article	English (source) Italian Mandarin Spanish
Vocal Tract Lab		articulatory synthesizer singing dona nobis pacem
Glove Talk		formant synthesis controlled by data glove, for further information see Sidney S. Fels and Geoffrey E. Hinton. Glove-TalkII: A neural network interface which maps gestures to parallel formant speech synthesizer controls. IEEE Transactions on Neural Networks. Volume 9. No. 1. Pages 205-212. 1998., see Sageev Oore demonstrate Glove Talk (43 Mb)
Pavarobotti		the singing robot: articulatory synthesis
HAL		From the film "2001: a space odyssey", the ideal (NOT a synthesizer but an actor!)	content sad/threatening regretful
First song in synthetic speech		"Bicycle Built for Two", Bell Laboratories, by Louis Gerstman and Max Mathews, 1961. This song was reprised by the `decorticated' Hal.
ESPER		Extracting Speaker Information From Children's Stories for Speech Synthesis: non-uniform unit selection
Feelix from Lola Canamero and Jacob Fredslund		Emotional music by Rasmus Lunding for a lego robot displaying emotions by mimic.
Luong Hieu-Thi et al		University of Science, Ho Chi Minh City, Vietnam, 2016. Experiment to construct a DNN based synthesizer, that inputs phonetic linguistic features and outputs acoustic features usable for a STRAIGHT synthesizer, from limited data of about 100 speakers while adding speakerid, age and gender information to the input and then testing several configurations with respect to speaker adaption, morphing and age and gender conversion by interchanging the relevant features and keeping the others fixed. See the paper the paper "Adapting and Controlling DNN-based Speech Synthesis using Input Codes" for details. Synthesized samples are from the 112 dimension Discriminant Condition configuration.	synthesized with model original/new speaker original/gender change original/younger original/older / / / /

Cosy Voice 2		End2end deep learning tts
Cosy Voice 2		End2end deep learning tts, style is author's voice
Coqui: Xtts-v2		End2end deep learning tts
Elevenlabs		End2end deep learning tts
F5-TTS		End2end deep learning tts, style is author's voice
Fish Speech 1.5		End2end deep learning tts
Hume Octave		End2end deep learning tts
Mars 5 TTS		End2end deep learning tts
Melo TTS		End2end deep learning tts
Metavoice TTS		End2end deep learning tts, style is author's voice
OpenAI FM ballad		End2end deep learning tts with instructions: connoisseur
OpenAI FM ballad		End2end deep learning tts with instructions: sports coach
Orpheus TTS		End2end deep learning tts
Parler TTS expresso		End2end deep learning tts, expresso model, with happy instruct
Parler TTS expresso		End2end deep learning tts, expresso model, with sadness instruct
Parler TTS MiniMultilingual V1.1		End2end deep learning tts, expresso model, with woman instruct
Parler TTS MiniMultilingual V1.1		End2end deep learning tts, expresso model, with man instruct
Piper TTS		End2end deep learning tts
Play.HT		End2end deep learning tts
Sesame		End2end deep learning tts
Sesame		End2end deep learning tts, style is author's voice
StyleTTS 2		End2end deep learning tts
Toucan tts		End2end deep learning tts
Zyphra tts		End2end deep learning tts
Zyphra tts		End2end deep learning tts, style is author's voice

• Altered.ai
• Metavoice
• Suno-ai
• Constructing emotional speech synthesizers with limited speech database by Ryosuke Tsuzuki, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Murtaza Bulut, Shrikanth S. Narayanan
• Synthesis of Emotional Speech Using Prosodically Balanced VCV Segments by Y. Niimi, M. Kasamatu, T. Nishimoto and M. Araki. Kyoto Institute of Technology
• DFKI's Safira Affective Speech Module P. Gebhard, E. Andre. DFKI
• "a high quality emotional speech synthesis method", Sakamoto & Saito. IBM Japan
• "Corpus-Based Emotional Speech Synthesis Based on Generation Process Model and Its Evaluation", Sato, Hirose & Minematsu. University of Tokyo
• Generation of Emotions by a Morphing Technique in English, French and Spanish by P. Boula de Mareüil, P. Célérier, J. Toen. LIMSI-CNRS/Elan

• MIT's Kismet
• Virtual Human Markup Language, Curtin University
• Emotional Speech Homepage of the DSPLab, university. of Maribor
• Geneva Emotion Research Group
• Affective Computing, MIT, Media Lab
• Jean-Marc Fellous and Eva Hudlicka: Emotion Home Page
• Christoph Bartneck's Affective Computing Portal

• March 24th 2025: added OpenAI fm samples
• March 20th 2025: added more Orpheus sample
• March 17th 2025: added more Sesame sample
• March 12th 2025: added more Parler samples
• March 10th 2025: added Zyphra sample
• February 27th 2025: added Hume.ai, Elevenlabs and metavoice samples
• January 28th 2025: added F5-TTS sample
• January 9th 2025: added Fish speech and Cosy Voice samples
• December 19th 2024: added Deep learning end2end samples
• March 23rd 2023: added Yuexin samples
• March 22nd 2023: added Kun Zhou samples
• February 23rd 2023: added Coqui samples
• January 10th 2023: added Vall-e samples
• April 1st 2022: added Meta sample
• June 30th 2020: added NIM sample and Uni Augsburg sample
• January 22nd 2019: added David sample
• January 8th 2019: added Tacotron sample
• April 19th 2018: added Lyrebird sample
• November 2nd 2016: added DNN speaker morphing samples
• September 12th 2016: added Deepmind WaveNet samples
• March 4th 2016: added Watson expressive Allison
• December 8th 2015: added Preserving Word-level Emphasis in Speech-to-speech Translation
• September 17th 2015; added adapting accent by articulatory copy.
• January 29th 2014; added Acapela emotional non uniform unit selection voices samples.
• September 18th 2013; added Voxygen arbitrary news sample.
• September 18th 2013; added Tuomo Raitio samples.
• November 20th 2012; added Voxygen samples.
• August 21th 2012; added Eva Szekely's samples based on audiobook extracts.
• July 18th 2012; added emofilt Mandarin Chinese samples.
• March 13th 2012; added Microsoft Voice Cloning samples.
• January 19th 2012; added Vivotext samples.
• February 22st 2011; added Mary Pavoque samples.
• February 21st 2011; added Ivona samples.
• February 15th 2011; added Speechconcept / CereProc samples.
• February 15th 2011; added Roberto Barra Chicote samples.
• February 8th 2011; added Syaheerah L. Lutfi samples.
• November 16th 2010; added Indian Institute of Technology Guwahati samples.
• July 12th 2010; added emofilt Spanish samples.
• August 24th 2009; added Trouvain / Schmidt's personality samples.
• May 4th 2009; added Sundaram laughter samples.
• May 4th 2009; added Beller laughter samples.
• April 28th 2009; added Rosec samples.
• Nov 5th 2008; added Moriyama samples.
• Oct 8th 2008; added Oytun Türk samples.
• February 5th 2008; added emofilt Dutch, Hungarian and Italian samples.
• Nov 2nd 2007; added Glove Talk and Vocal Tract Lab and IBM Fernandez samples.
• Oct 11th 2006; added Mariet Theune samples.
• June 19th 2006; added Audibert samples.
• February 17th 2006; added MARY unit selection samples.
• Decemer 14th 2005; added Beller samples.
• October 14th 2005; added Cepstral samples.
• October 10th 2005; added Sail voice conversion samples.
• September 19th 2005; added J.P. Cabral samples.
• August 29th 2005; added ESPER sample.
• August 9th 2005; added Metaface sample.
• August 3rd 2005; added emofilt Greek and Turkish samples.
• April 29th 2005; added Loquendo extralinguistics Stefan sample.
• April 25th 2005; added Loquendo extralinguistics samples.
• March 14th 2005; added Gregor Hofer samples.
• March 5th 2005; added ESP project.
• March 2nd 2005; added Kobayashi samples.
• February 16th 2005; added new emofilt samples.
• February 15th 2005; added Piero Cosi samples and PF-Star project.
• September 24th 2004; added more Oudeyer samples
• September 10th 2004; added Bulut/Narayanan/Syrdal samples
• September 2nd 2004; added Feelix sample
• August 27th 2004; added Ignasi Iriondo and Nick Campbell samples
• August 5th 2004; added Stephan Baldes' samples
• August 4th 2004; added Kismet (affect editor) samples with words
• August 2nd 2004; added Rhetorical's Eduardo sample
• July 6th 2004; added IBM Watson Lab samples
• July 4th 2004; added Loquendo samples
• June 23th 2004: added ProTalker

Demos of TTS-Systems for German

comments: felixbur@gmx.de

band