Generating segmental foreign accent

García Lecumberri, María Luisa and Barra Chicote, Roberto and Pérez Ramón, Rubén and Yamagishi, Junichi and Cooke, Martin (2014). Generating segmental foreign accent. In: "15th Annual Conference of the Internacional Speech Communication Association (Interspeech 2014)", 14/09/2014 - 18/09/2014, Singapore. pp. 1302-1306.

Description

Title: Generating segmental foreign accent
Author/s:
  • García Lecumberri, María Luisa
  • Barra Chicote, Roberto
  • Pérez Ramón, Rubén
  • Yamagishi, Junichi
  • Cooke, Martin
Item Type: Presentation at Congress or Conference (Article)
Event Title: 15th Annual Conference of the Internacional Speech Communication Association (Interspeech 2014)
Event Dates: 14/09/2014 - 18/09/2014
Event Location: Singapore
Title of Book: 15th Annual Conference of the Internacional Speech Communication Association (Interspeech 2014)
Date: 2014
Subjects:
Freetext Keywords: Foreign accent, speech synthesis, splicing
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería Electrónica
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

For most of us, speaking in a non-native language involves deviating to some extent from native pronunciation norms. However, the detailed basis for foreign accent (FA) remains elusive, in part due to methodological challenges in isolating segmental from suprasegmental factors. The current study examines the role of segmental features in conveying FA through the use of a generative approach in which accent is localised to single consonantal segments. Three techniques are evaluated: the first requires a highly-proficiency bilingual to produce words with isolated accented segments; the second uses cross-splicing of context-dependent consonants from the non-native language into native words; the third employs hidden Markov model synthesis to blend voice models for both languages. Using English and Spanish as the native/non-native languages respectively, listener cohorts from both languages identified words and rated their degree of FA. All techniques were capable of generating accented words, but to differing degrees. Naturally-produced speech led to the strongest FA ratings and synthetic speech the weakest, which we interpret as the outcome of over-smoothing. Nevertheless, the flexibility offered by synthesising localised accent encourages further development of the method.

Funding Projects

TypeCodeAcronymLeaderTitle
FP7287678SIMPLE4ALLUniversity of EdinburghSpeech synthesis that improves through adaptive learning
Government of SpainDPI2010-21247-C02-02UnspecifiedUnspecifiedUnspecified

More information

Item ID: 37539
DC Identifier: http://oa.upm.es/37539/
OAI Identifier: oai:oa.upm.es:37539
Deposited by: Memoria Investigacion
Deposited on: 20 Oct 2015 15:51
Last Modified: 06 Jun 2016 15:51
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM