Breathing and Speech Planning in Spontaneous Speech Synthesis
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7649-7653
Abstract
Breathing and speech planning in spontaneous speech are coordinated processes, often exhibiting disfluent patterns. While synthetic speech is not subject to respiratory needs, integrating breath into synthesis has advantages for naturalness and recall. At the same time, a synthetic voice reproducing disfluent breathing patterns learned from the data can be problematic. To address this, we first propose training stochastic TTS on a corpus of overlapping breath-group bigrams, to take context into account. Next, we introduce an unsupervised automatic annotation of likely-disfluent breath events, through a product-of-experts model that combines the output of two breath- event predictors, each using complementary information and operating in opposite directions. This annotation enables creating an automatically-breathing spontaneous speech synthesiser with a more fluent breathing style. A subjective evaluation on two spoken genres (impromptu and rehearsed) found the proposed system to be preferred over the baseline approach treating all breath events the same.Keywords
This publication has 25 references indexed in Scilit:
- Phrase Break Prediction for Long-Form Reading TTS: Exploiting Text Structure Information2017
- Respiratory Constraints in Verbal and Non-verbal CommunicationFrontiers in Psychology, 2017
- Detecting a targeted voice style in an audiobook using voice quality features2012
- Breath Group Analysis for Reading and Spontaneous Speech in Healthy AdultsFolia Phoniatrica et Logopaedica, 2010
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- Cognitive-Linguistic Demands and Speech BreathingJournal of Speech, Language, and Hearing Research, 1996
- The effects of breath sounds on the perception of synthetic speechThe Journal of the Acoustical Society of America, 1995
- Variability and Consistency in Speech Breathing During ReadingJournal of Speech, Language, and Hearing Research, 1994
- Signal estimation from modified short-time Fourier transformIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- Temporal Patterns of Cognitive Activity and Breath Control in SpeechLanguage and Speech, 1965