Non-native speech conversion with consistency-aware recursive network and generative adversarial network

Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Hiroyasu Ando, Kaoru Hiramatsu, Kunio Kashino

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

This paper deals with the problem of automatically correcting the pronunciation of non-native speakers. Since the pronunciation characteristics of non-native speakers depend heavily on the context (such as words), conversion rules for correcting pronunciation should be learned from a sequence of features rather than a single-frame feature. For the online conversion of local sequences of features, we construct a neural network (NN) that takes a sequence of features as an input/output, generates a sequence of features in a segment-by- segment fashion and guarantees the consistency of the generated features within overlapped segments. Futhermore, we apply a recently proposed generative adversarial network (GAN)-based postfilter to the generated feature sequence with the aim of synthesizing natural-sounding speech. Through subjective and quantitative evaluations, we confirmed the superiority of our proposed method over a conventional NN approach in terms of conversion quality.

Original languageEnglish
Title of host publicationProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages182-188
Number of pages7
ISBN (Electronic)9781538615423
DOIs
Publication statusPublished - 2018 Feb 5
Externally publishedYes
Event9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017 - Kuala Lumpur, Malaysia
Duration: 2017 Dec 122017 Dec 15

Publication series

NameProceedings - 9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
Volume2018-February

Other

Other9th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017
Country/TerritoryMalaysia
CityKuala Lumpur
Period17/12/1217/12/15

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Non-native speech conversion with consistency-aware recursive network and generative adversarial network'. Together they form a unique fingerprint.

Cite this