Expressive speech synthesis using a concatenative synthesizer

This paper describes an experiment in synthesizing four emotional states - anger, happiness, sadness and neutral – using a concatenative speech synthesizer. To achieve this, five emotionally (i.e., semantically) unbiased target sentences were prepared. Then, separate speech inventories, comprising the target diphones for each of the above emotions, were recorded. Using the 16 different combinations of prosody and inventory during synthesis resulted in 80 synthetic test sentences. The results were evaluated by conducting listening tests with 33 naive listeners. Synthesized anger was recognized with 86.1% accuracy, sadness with 89.1%, happiness with 44.2%, and neutral emotion with 81.8% accuracy. According to our results, anger was classified as inventory dominant and sadness and neutral as prosody dominant. Results were not sufficient to make similar conclusions regarding happiness. The highest recognition accuracies were achieved for sentences synthesized by using prosody and diphone inventory belonging to the same emotion.

• Publication year

  2002

• Venue

  Interspeech

• Publication date

  2002-09-16

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.21437/ICSLP.2002-389
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• PERSONALITY PROCESSES AND INDIVIDUAL DIFFERENCES Universals and Cultural Differences in the Judgments of Facial Expressions of Emotion

  2004cited by this paper
• Influence of emotion and focus location on prosody in matched statements and questions.

  2001cited by this paper
• A cross-cultural investigation of emotion inferences from voice and speech: implications for speech technology

  2000cited by this paper
• A Speech Synthesis System with Emotion for Assisting Communication

  2000cited by this paper
• THEORETICAL APPROACHES TO EMOTION

  2000cited by this paper
• ANALYSIS AND MODELLING OF EMOTIONAL SPEECH IN SPANISH

  1999cited by this paper
• Generating emotional speech with a concatenative synthesizer

  1998cited by this paper
• Emotions in time domain synthesis

  1996cited by this paper
• Emotional stress in synthetic speech: Progress and future directions

  1996cited by this paper
• Applying analysis of human emotional speech to enhance synthetic speech

  1993cited by this paper
• Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones

  1989cited by this paper

• Position: Towards Responsible Evaluation for Text-to-Speech

  2025cites this paper
• Making Social Platforms Accessible: Emotion-Aware Speech Generation with Integrated Text Analysis

  2024cites this paper
• Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey

  2024cites this paper
• Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey

  2024cites this paper
• Personality Shifting Agent to Remove Users' Negative Impression on Speech Recognition Failure

  2021cites this paper
• Incorporation of Happiness in Neutral Speech by Modifying Time-Domain Parameters of Emotive-Keywords

  2021cites this paper
• Designing Personality Shifting Agent for Speech Recognition Failure

  2021cites this paper
• Exemplar-Based Emotive Speech Synthesis

  2021cites this paper
• Building a controllable expressive speech synthesis system with multiple emotion strengths

  2020cites this paper
• Dialogue act based expressive speech synthesis in limited domain for the Czech language

  2020cites this paper
• Controlling Emotion Strength with Relative Attribute for End-to-End Speech Synthesis

  2019cites this paper
• Control Emotion Intensity for LSTM-Based Expressive Speech Synthesis

  2019cites this paper
• Prosody modification for speech recognition in emotionally mismatched conditions

  2018cites this paper
• Analysis on speech signal features of manic patients.

  2018cites this paper
• Databases, features and classifiers for speech emotion recognition: a review

  2018cites this paper
• Emotional speech synthesis based on DNN and PAD emotional state model

  2018cites this paper
• A DNN-based emotional speech synthesis by speaker adaptation

  2018cites this paper
• Automatic acoustic synthesis of human-like laughtera )

  2017cites this paper
• Word and paragraph embeddings for expresive speech synthesis

  2017cites this paper
• Using Mandarin Training Corpus to Realize a Mandarin-Tibetan Cross-Lingual Emotional Speech Synthesis

  2017cites this paper
• Dimensional paralinguistic information control based on multiple-regression HSMM for spontaneous dialogue speech synthesis with robust parameter estimation

  2017cites this paper
• Construction of Japanese Audio-Visual Emotion Database and Its Application in Emotion Recognition

  2016cites this paper
• Emotional Speech Recognition

  2016cites this paper
• Design of a Speech Corpus for Research on Cross-Lingual Prosody Transfer

  2016cites this paper
• Online The Open University ’ s repository of research publications and other research outputs Fully generated scripted dialogue for embodied agents

  2016cites this paper
• Prosodic Parameters and Prosodic Structures of French Emotional Data

  2016cites this paper
• Design and Evaluation of Statistical Parametric Techniques in Expressive Text-To-Speech: Emotion and Speaking Styles Transplantation

  2016cites this paper
• Generation of Audio-Visual Prosody for Expressive Virtual Actors. (Génération de la Prosodie Audio-Visuelle pour les Acteurs Virtuels Expressifs )

  2015cites this paper
• Vowel-Based Non-uniform Prosody Modification for Emotion Conversion

  2015cites this paper
• Conversion of neutral speech to storytelling style speech

  2015cites this paper
• ENHANCED SENTIMENTAL ANALYSIS FOR SPEECH SYNTHESIS BASED ON PROSODY FEATURE MODIFICATION USING TD-PSOLA TECHNIQUE FOR ENGLISH

  2015cites this paper
• Telugu emotional story speech synthesis using SABLE markup language

  2015cites this paper
• The SP2 SCOPES Project on Speech Prosody

  2014cites this paper
• Incorporation of happiness into neutral speech by modifying emotive-keywords

  2014cites this paper
• Memorable spoken quote corpora of TED public speaking

  2014cites this paper
• Approximation Neural Network for Phoneme Synthesis

  2014cites this paper
• Predicting synthetic voice style from facial expressions. An application for augmented conversations

  2014cites this paper
• A review of paralinguistic information processing for natural speech communication

  2013cites this paper
• Real-time concatenative synthesis for networked musical interactions

  2013cites this paper
• Emotional Speech Synthesis Based on Prosodic Feature Modification

  2013cites this paper
• Musical Acoustics Session 2 pMU : Musical Preference , Perception , and Processing 2 pMU 13 . Real-time concatenative synthesis for networked musical interactions

  2013cites this paper
• Emotional Speech Synthesis Based on Prosodic Feature Modification

  2013cites this paper
• The Good Our Field Can Hope to Do, the Harm It Should Avoid

  2012cites this paper
• Czech Expressive Speech Synthesis in Limited Domain - Comparison of Unit Selection and HMM-Based Approaches

  2012cites this paper
• Fundamental frequency adjustment and formant transition based emotional speech synthesis

  2012cites this paper
• Acoustic analysis of czech expressive recordings from a single speaker in terms of various communicative functions

  2011cites this paper
• Analysis-by-Performance: Gesturally-Controlled Voice Synthesis as an Input for Modelling of Vibrato in Singing

  2011cites this paper
• Speech Synthesis Systems in Ambient Intelligence Environments

  2010cites this paper
• Extraction of Speech Parameters Relating to the Characteristics of Emotional Expression:Focus on the Attentiveness

  2010cites this paper
• Shodhika Bhashini Multilingual Search and TTS System

  2010cites this paper
• Special Speech Synthesis for Social Network Websites

  2010cites this paper
• Modeling the Expressivity of Input Text Semantics for Chinese Text-to-Speech Synthesis in a Spoken Dialog System

  2009cites this paper
• High Quality Emotional HMM-Based Synthesis in Spanish

  2009cites this paper
• Expressive Speech Synthesis Using Prosodic Modification and Dynamic Time Warping

  2009cites this paper
• A Methodological Approach for Building Multimodal Acted Affective Databases

  2009cites this paper
• Determinism in speech pitch relation to emotion

  2009cites this paper
• Further Investigation of MDS as a Tool for Evaluation of Speech Quality of Synthesized Speech

  2009cites this paper
• Expressive Speech Synthesis: Past, Present, and Possible Futures

  2009cites this paper
• Prosodic Analysis and Modelling of Conversational Elements for Speech Synthesis.

  2009influential citation
• On the robustness of overall F0-only modifications to the perception of emotions in speech.

  2008cites this paper
• Expressive/Affective Speech Synthesis

  2008cites this paper
• Transforming high-effort voices into breathy voices using adaptive pre-emphasis linear prediction

  2008cites this paper
• Toward Efficient Low Cost Highly Accurate Emotion speech Synthesizer

  2008cites this paper
• Recognition for synthesis: Automatic parameter selection for resynthesis of emotional speech from neutral speech

  2008cites this paper
• Extra: A Culturally Enriched Malay Text to Speech System.

  2008cites this paper
• Single Speaker Acoustic Analysis of Czech Speech for Purposes of Emotional Speech Synthesis

  2008cites this paper
• Subjective Evaluation of an Emotional Speech Database for Basque

  2008cites this paper
• Euskarazko datu base emoziodun baten ebaluaketa subjektiboa

  2008cites this paper
• Dialog speech acts and prosody: considerations for TTS

  2008cites this paper
• Prosodie de la parole expressive : dimensionnalité d'énoncés méthodologiquement contrôlés authentiques et actés. (Prosody of expressive speech: dimensionality of methodologically controlled authentic and acted utterances)

  2008cites this paper
• Expressive Speech Synthesis Using Emotion-Specific Speech Inventories

  2008influential citation
• Applying an analysis of acted vocal emotions to improve the simulation of synthetic speech

  2008cites this paper
• Primitives-based evaluation and estimation of emotions in speech

  2007cites this paper
• ANALYZING EMOTIONS IN SPOKEN ROMANIAN

  2007cites this paper
• Automatic exploration of corpus-specific properties for expressive text-to-speech: a case study in emphasis

  2007cites this paper
• A Study on Speech with Manifest Emotions

  2007cites this paper
• Database Mining for Flexible Concatenative Text-to-Speech

  2007cites this paper
• ADDING EMOTIONS TO SYNTHESIZED MALAY SPEECH USING DIPHONE-BASED TEMPLATES

  2007cites this paper
• Requirements for Spoken Conversational Agents in Games

  2006cites this paper
• Shaping human behavior by observing mobility gestures

  2006cites this paper
• The IBM expressive text-to-speech synthesis system for American English

  2006cites this paper
• Applying SFC Model for Chinese Expressive Speech Synthesis

  2006cites this paper
• De E-Wiz à C-Clone. Recueil, modélisation et synthèse d'expressions authentiques

  2006cites this paper
• Database Pruning for Unsupervised Building of Text-To-Speech Voices

  2006cites this paper
• Emotional speech recognition: Resources, features, and methods

  2006cites this paper
• Expressive speech synthesis: evaluation of a voice quality centered coder on the different acoustic dimensions

  2006cites this paper
• FACULTY OF APPLIED SCIENCES COMMUNICATION OF EMOTIONS FOR E-CREATURES

  2006cites this paper
• Towards Expressive Speech Synthesis in English on a Robotic Platform

  2006cites this paper
• Generating expressive speech for storytelling applications

  2006cites this paper
• Categorical perception of vocal emotion expressions.

  2005cites this paper
• A multi-modal approach to selective interaction in assistive domains

  2005cites this paper
• Prosodic Reading Style Simulation for Text-to-Speech Synthesis

  2005cites this paper
• Prosody analysis and modeling for emotional speech synthesis

  2005cites this paper
• The prosodic dimensions of emotion in speech: the relative weights of parameters

  2005cites this paper
• Adding Emotions to Malay Synthesized Speech Using Diphone-based Templates

  2005cites this paper
• A Model-Based Experiment towards an Emotional Syn- thesis

  2005cites this paper
• Underlying Principles of a High-quality Speech Manipulation System STRAIGHT and Its Application to Speech Segregation

  2005cites this paper
• Investigating the role of phoneme-level modifications in emotional speech resynthesis

  2005cites this paper
• Estonian rhythm and the Pairwise Variability Index

  2005cites this paper
• Intonation Modelling and Adaptation for Emotional Prosody Generation

  2005cites this paper