@inproceedings{brognaux-etal-2016-combining,
title = "Combining Manual and Automatic Prosodic Annotation for Expressive Speech Synthesis",
author = "Brognaux, Sandrine and
Fran{\c{c}}ois, Thomas and
Saerens, Marco",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1613",
pages = "3872--3879",
abstract = "Text-to-speech has long been centered on the production of an intelligible message of good quality. More recently, interest has shifted to the generation of more natural and expressive speech. A major issue of existing approaches is that they usually rely on a manual annotation in expressive styles, which tends to be rather subjective. A typical related issue is that the annotation is strongly influenced ― and possibly biased ― by the semantic content of the text (e.g. a shot or a fault may incite the annotator to tag that sequence as expressing a high degree of excitation, independently of its acoustic realization). This paper investigates the assumption that human annotation of basketball commentaries in excitation levels can be automatically improved on the basis of acoustic features. It presents two techniques for label correction exploiting a Gaussian mixture and a proportional-odds logistic regression. The automatically re-annotated corpus is then used to train HMM-based expressive speech synthesizers, the performance of which is assessed through subjective evaluations. The results indicate that the automatic correction of the annotation with Gaussian mixture helps to synthesize more contrasted excitation levels, while preserving naturalness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brognaux-etal-2016-combining">
<titleInfo>
<title>Combining Manual and Automatic Prosodic Annotation for Expressive Speech Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandrine</namePart>
<namePart type="family">Brognaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Saerens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text-to-speech has long been centered on the production of an intelligible message of good quality. More recently, interest has shifted to the generation of more natural and expressive speech. A major issue of existing approaches is that they usually rely on a manual annotation in expressive styles, which tends to be rather subjective. A typical related issue is that the annotation is strongly influenced ― and possibly biased ― by the semantic content of the text (e.g. a shot or a fault may incite the annotator to tag that sequence as expressing a high degree of excitation, independently of its acoustic realization). This paper investigates the assumption that human annotation of basketball commentaries in excitation levels can be automatically improved on the basis of acoustic features. It presents two techniques for label correction exploiting a Gaussian mixture and a proportional-odds logistic regression. The automatically re-annotated corpus is then used to train HMM-based expressive speech synthesizers, the performance of which is assessed through subjective evaluations. The results indicate that the automatic correction of the annotation with Gaussian mixture helps to synthesize more contrasted excitation levels, while preserving naturalness.</abstract>
<identifier type="citekey">brognaux-etal-2016-combining</identifier>
<location>
<url>https://aclanthology.org/L16-1613</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3872</start>
<end>3879</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Manual and Automatic Prosodic Annotation for Expressive Speech Synthesis
%A Brognaux, Sandrine
%A François, Thomas
%A Saerens, Marco
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F brognaux-etal-2016-combining
%X Text-to-speech has long been centered on the production of an intelligible message of good quality. More recently, interest has shifted to the generation of more natural and expressive speech. A major issue of existing approaches is that they usually rely on a manual annotation in expressive styles, which tends to be rather subjective. A typical related issue is that the annotation is strongly influenced ― and possibly biased ― by the semantic content of the text (e.g. a shot or a fault may incite the annotator to tag that sequence as expressing a high degree of excitation, independently of its acoustic realization). This paper investigates the assumption that human annotation of basketball commentaries in excitation levels can be automatically improved on the basis of acoustic features. It presents two techniques for label correction exploiting a Gaussian mixture and a proportional-odds logistic regression. The automatically re-annotated corpus is then used to train HMM-based expressive speech synthesizers, the performance of which is assessed through subjective evaluations. The results indicate that the automatic correction of the annotation with Gaussian mixture helps to synthesize more contrasted excitation levels, while preserving naturalness.
%U https://aclanthology.org/L16-1613
%P 3872-3879
Markdown (Informal)
[Combining Manual and Automatic Prosodic Annotation for Expressive Speech Synthesis](https://aclanthology.org/L16-1613) (Brognaux et al., LREC 2016)
ACL