Litcius/Paper detail

End-To-End Accent Conversion Without Using Native Utterances

Songxiang Liu, Disong Wang, Yuewen Cao, Lifa Sun, Xixin Wu, Shiyin Kang, Zhiyong Wu, Xunying Liu, Dan Su, Dong Yu, Helen Meng

202035 citationsDOI

Abstract

Techniques for accent conversion (AC) aim to convert non-native to native accented speech. Conventional AC methods try to convert only the speaker identity of a native speaker's voice to that of the non-native accented target speaker, leaving the underlying content and pronunciations unchanged. This hinders their practical use in real-world applications, because native-accented utterances are required at conversion stage. In this paper, we present an end-to-end framework, which is able to conduct AC from non-native-accented utterances without using any native-accented utterances during online conversion. We achieve this by independently extracting linguistic and speaker representations from non-native accented speech and condition a speech synthesis model on these representations to generate native-accented speech. Experiments on open-source data corpora show that the proposed system can convert Hindi-accented English speech into native American English speech with high naturalness, which is indistinguishable from native-accented recordings in terms of accent.

Topics & Concepts

NaturalnessStress (linguistics)Computer scienceSpeech recognitionSpeech synthesisFirst languageIdentity (music)Native americanLinguisticsNatural language processingArtificial intelligenceHistoryAcousticsQuantum mechanicsPhilosophyEthnologyPhysicsSpeech Recognition and SynthesisNatural Language Processing TechniquesSpeech and dialogue systems
End-To-End Accent Conversion Without Using Native Utterances | Litcius