Emphasis recreation for TTS using intonation atoms

Honnet, Pierre-Edouard; Garner, Philip N.

doi:10.21437/ssw.2016-3

Cited by 3 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A phrase additionally consists of a phrase atom (phrase command in CR model) which models the general shape of the contour and is correlated mainly to the physics of the speakers' lung volume (dotted line in upper plot of Figure 1). Experiments have shown that the proposed model is capable of producing good representations and can transplant emphasis from one language to another [12].…”

Section: Relation To Prior Workmentioning

confidence: 99%

A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation

Schnell¹,

Garner²

2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

The Generalised Command Response (GCR) model is a timelocal model of intonation that has been shown to lend itself to (cross-language) transfer of emphasis. In order to generalise the model to longer prosodic sequences, we show that it can be driven by a recurrent neural network emulating a spiking neural network. We show that a loss function for error backpropagation can be formulated analogously to that of the Spike Pattern Association Neuron (SPAN) method for spiking networks. The resulting system is able to generate prosody comparable to a state-of-the-art deep neural network implementation, but potentially retaining the transfer capabilities of the GCR model.

show abstract

Section: Relation To Prior Workmentioning

confidence: 99%

A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation

Schnell¹,

Garner²

2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, however, this gap has been closed to some extent by studies by Delić et al (2016), Szaszák et al (2016) and , who have shown that GCR atoms correlate rather well with ToBI markers, and can help with detection of emphasis (or stress). Honnet and Garner (2016) have also shown that GCR can be used to synthesise emphasis. Aside from being reassuring, this is intuitive in that ToBI is a mechanism for constructing linguistic cues; it is a semantic level below that of the cues themselves.…”

Section: Linguistic Meaningmentioning

confidence: 99%

Intonation modelling using a muscle model and perceptually weighted matching pursuit

Honnet

Gerazov

Gjoreski

et al. 2018

Speech Communication

Self Cite

View full text Add to dashboard Cite

We propose a physiologically based intonation model using perceptual relevance. Motivated by speech synthesis from a speech-to-speech translation (S2ST) point of view, we aim at a language independent way of modelling intonation. The model presented in this paper can be seen as a generalisation of the command response (CR) model, albeit with the same modelling power. It is an additive model which decomposes intonation contours into a sum of critically damped system impulse responses. To decompose the intonation contour, we use a weighted correlation based atom decomposition algorithm (WCAD) built around a matching pursuit framework. The algorithm allows for an arbitrary precision to be reached using an iterative procedure that adds more elementary atoms to the model. Experiments are presented demonstrating that this generalised CR (GCR) model is able to model intonation as would be expected. Experiments also show that the model produces a similar number of parameters or elements as the CR model. We conclude that the GCR model is appropriate as an engineering solution for modelling prosody, and hope that it is a contribution to a deeper scientific understanding of the neurobiological process of intonation.

show abstract

“…Some researchers have tried to apply ideas of classical intonation models by predicting their meanings (Chakrasali et al, 2022;Kuczmarski, 2021;Marelli et al, 2019) or identifying intonation segments (Alvarez et al, 2022). Other intonation modelling instances include the transfer of intonation components into neutral synthesized speech (Honnet and Garner, 2016), unsupervised or supervised training of latent prosody space (Sun et al, 2020;Raitio et al, 2020Raitio et al, , 2022. In Birkholz and Zhang (2020), microprosody-based intonation modelling is presented as an additional way of improving the naturalness of synthesized speech.…”

Section: Introductionmentioning

confidence: 99%

An Overview of Lithuanian Intonation: A Linguistic and Modelling Perspective

Melnik-Leroy¹,

Bernatavičienė²,

Korvel³

et al. 2022

Informatica

View full text Add to dashboard Cite

Intonation is a complex suprasegmental phenomenon essential for speech processing. However, it is still largely understudied, especially in the case of under-resourced languages, such as Lithuanian. The current paper focuses on intonation in Lithuanian, a Baltic pitch-accent language with free stress and tonal variations on accented heavy syllables. Due to historical circumstances, the description and analysis of Lithuanian intonation were carried out within different theoretical frameworks and in several languages, which makes them hardly accessible to the international research community. This paper is the first attempt to gather research on Lithuanian intonation from both the Lithuanian and the Western traditions, the structuralist and generativist points of view, and the linguistic and modelling perspectives. The paper identifies issues in existing research that require special attention and proposes directions for future investigations both in linguistics and modelling.

show abstract

Emphasis recreation for TTS using intonation atoms

Cited by 3 publications

References 17 publications

A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation

A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation

Intonation modelling using a muscle model and perceptually weighted matching pursuit

An Overview of Lithuanian Intonation: A Linguistic and Modelling Perspective

Contact Info

Product

Resources

About