Prosody in speech synthesis: the interplay between basic research and TTS application

  title={Prosody in speech synthesis: the interplay between basic research and TTS application},
  author={Klaus J. Kohler},
  journal={Journal of Phonetics},
  • K. Kohler
  • Published 1991
  • Linguistics
  • Journal of Phonetics

The Kiel Intonation Model (KIM), its Implementation in TTS Synthesis and its Application to the Study of Spontaneous Speech

The Kiel Intonation Model for German is outlined, incorporating stress and intonation, timing and articulatory reduction, and sets out the prosodic notation system, which is the basis for prosodic labelling of speech data.

Intonation segments and segmental intonation

An acoustic analysis of a German dialogue corpus showed that the sound qualities and durations of fricatives, vocoids, and diphthongs at the ends of question and statement utterances varied systematically with the utterance-final intonation segments, suggesting that these variations are meant to support the pitch course.

Perception of Intonation

This paper provides an overview of the role of intonation (prosody) in speech communication, with special focus on the perception of intonation contours. Why there is no complete theory? why is it

At the Edge of Intonation: The Interplay of Utterance-Final F0 Movements and Voiceless Fricative Sounds

Investigation of the interplay of F0 and voiceless fricatives in speech production crosses the traditional segment-prosody divide and finds different spectral-energy patterns are suitable to induce percepts of a high ‘aperiodic pitch’ at the end of the questions and of a low “aperiodics pitch” at theend of the statements.

A Predictive Model of Prosody Through Grammatical Interface: A computational Approach

It is shown that prosodic features can be reliably predicted from a set of features that encode the phonetic, phonological, syntactic, semantic, and semantic properties of an utterance.

Acoustic Patterns and Communicative Functions of Phrase-Final F0 Rises in German: Activating and Restricting Contours

Acoustic features and communicative functions of phrase-final F0 rises starting before an accented-vowel onset are analysed in a corpus of German unscriptedspeech, and the range proportion differentiates between two patterns.

Coding of intonational meanings beyond F0: evidence from utterance-final /t/ aspiration in German.

  • O. Niebuhr
  • Physics
    The Journal of the Acoustical Society of America
  • 2008
Noise patterns found in connection with early and late peak productions were able to change the attitudinal meaning of the stimuli toward the meaning profile of the respective F0 peak category, suggesting that final aspirations can be part of the coding of meanings.

Shaping phrase-final rising intonation in German

In German, the course of phrase-final rising intonation can be modelled by an interpolation between three points in the pitch contour, giving a more appropriate description than current approaches to

The Signalling of German Rising-Falling Intonation Categories – The Interplay of Synchronization, Shape, and Height

The findings corroborate the existence of all three categories in German intonation and support the idea that the timing of the peakmovements with regard to the accented vowel is important for their perceptualdifferentiation.

Lexical and Acoustic Modelling of Swedish Prosody

A stylization-based model, where temporal and frequency information is extracted directly from actual F0 contours, and Taylor's tilt model, which parameterizes the contours using a mathematical function are selected for continued work in the thesis.



Swedish Prosody

The model was first set up for statement intonation in isolated sentences from five prototype dialects, and later applied to interrogativeintonation, to transitional forms between the prototype dialectS, to Greek and French intonations and to prosodic transfer in a foreign accent.

A preliminary description of German intonation

Some perceptually relevant characteristics of German intonation are described and some stylized German pitch contours are presented, which can be considered to be a perceptually adequate approximation of pitch contour in natural utterances.

Sentence Intonation in Swedish

This paper shows how the proposed schema for generating fundamental frequency patterns of statements in four Swedish dialects can be applied to two different interrogative frames, one for yes/no questions with non-inverted word order and one for inverted order.

Cross-Language Use of Pitch: An Ethological View

Patterns in signaling functions of the pitch of voice can be explained by the assumption that human vocal communication exploits the ‘frequency code’, a cross-species association of high pitch vocalizations with smallness, lack of threat, and of low pitch vocalization with the vocalizer’s largeness and threatening intent.

The intonation of American English

This study explains the structure of the English intonation system in relation to the structural systems of stress, pause, and rhythm.

Automatic time alignment of speech with a phonetic transcription

In the present study, only two parameters have been used; the intensity of the speech signal below 400 Hz and the intensity above 500 Hz; it is shown that this very coarse information is enough to give a correct segmentation in most cases.

An Ethological Perspective on Common Cross-Language Utilization of F₀ of Voice

It is argued that cross-language similarities in the intonation contours for statements versus questions and the existence of sexual dimorphism in the vocal anatomy of humans (and certain non humans) all arise due to an innately specified ‘frequency code’.

Rule‐controlled data base search

A speech analysis system to attempt to alleviate the problems in administering huge speech data bases, both to transcribe and segment the speech and to easily access stored material.