@inproceedings{burkhardt-reichel-2016-taxonomy,
title = "A Taxonomy of Specific Problem Classes in Text-to-Speech Synthesis: Comparing Commercial and Open Source Performance",
author = "Burkhardt, Felix and
Reichel, Uwe D.",
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/L16-1118",
pages = "744--749",
abstract = "Current state-of-the-art speech synthesizers for domain-independent systems still struggle with the challenge of generating understandable and natural-sounding speech. This is mainly because the pronunciation of words of foreign origin, inflections and compound words often cannot be handled by rules. Furthermore there are too many of these for inclusion in exception dictionaries. We describe an approach to evaluating text-to-speech synthesizers with a subjective listening experiment. The focus is to differentiate between known problem classes for speech synthesizers. The target language is German but we believe that many of the described phenomena are not language specific. We distinguish the following problem categories: Normalization, Foreign linguistics, Natural writing, Language specific and General. Each of them is divided into five to three problem classes. Word lists for each of the above mentioned categories were compiled and synthesized by both a commercial and an open source synthesizer, both being based on the non-uniform unit-selection approach. The synthesized speech was evaluated by human judges using the Speechalyzer toolkit and the results are discussed. It shows that, as expected, the commercial synthesizer performs much better than the open-source one, and especially words of foreign origin were pronounced badly by both systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burkhardt-reichel-2016-taxonomy">
<titleInfo>
<title>A Taxonomy of Specific Problem Classes in Text-to-Speech Synthesis: Comparing Commercial and Open Source Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Burkhardt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Reichel</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>Current state-of-the-art speech synthesizers for domain-independent systems still struggle with the challenge of generating understandable and natural-sounding speech. This is mainly because the pronunciation of words of foreign origin, inflections and compound words often cannot be handled by rules. Furthermore there are too many of these for inclusion in exception dictionaries. We describe an approach to evaluating text-to-speech synthesizers with a subjective listening experiment. The focus is to differentiate between known problem classes for speech synthesizers. The target language is German but we believe that many of the described phenomena are not language specific. We distinguish the following problem categories: Normalization, Foreign linguistics, Natural writing, Language specific and General. Each of them is divided into five to three problem classes. Word lists for each of the above mentioned categories were compiled and synthesized by both a commercial and an open source synthesizer, both being based on the non-uniform unit-selection approach. The synthesized speech was evaluated by human judges using the Speechalyzer toolkit and the results are discussed. It shows that, as expected, the commercial synthesizer performs much better than the open-source one, and especially words of foreign origin were pronounced badly by both systems.</abstract>
<identifier type="citekey">burkhardt-reichel-2016-taxonomy</identifier>
<location>
<url>https://aclanthology.org/L16-1118</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>744</start>
<end>749</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Taxonomy of Specific Problem Classes in Text-to-Speech Synthesis: Comparing Commercial and Open Source Performance
%A Burkhardt, Felix
%A Reichel, Uwe D.
%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 burkhardt-reichel-2016-taxonomy
%X Current state-of-the-art speech synthesizers for domain-independent systems still struggle with the challenge of generating understandable and natural-sounding speech. This is mainly because the pronunciation of words of foreign origin, inflections and compound words often cannot be handled by rules. Furthermore there are too many of these for inclusion in exception dictionaries. We describe an approach to evaluating text-to-speech synthesizers with a subjective listening experiment. The focus is to differentiate between known problem classes for speech synthesizers. The target language is German but we believe that many of the described phenomena are not language specific. We distinguish the following problem categories: Normalization, Foreign linguistics, Natural writing, Language specific and General. Each of them is divided into five to three problem classes. Word lists for each of the above mentioned categories were compiled and synthesized by both a commercial and an open source synthesizer, both being based on the non-uniform unit-selection approach. The synthesized speech was evaluated by human judges using the Speechalyzer toolkit and the results are discussed. It shows that, as expected, the commercial synthesizer performs much better than the open-source one, and especially words of foreign origin were pronounced badly by both systems.
%U https://aclanthology.org/L16-1118
%P 744-749
Markdown (Informal)
[A Taxonomy of Specific Problem Classes in Text-to-Speech Synthesis: Comparing Commercial and Open Source Performance](https://aclanthology.org/L16-1118) (Burkhardt & Reichel, LREC 2016)
ACL