Data-Driven Enhancement of State Mapping-Based Cross-Lingual Speaker Adaptation

نویسنده

  • Hui LIANG
چکیده

in French cadre d’adaptation axé sur les données et utilisant des connaissances phonologiques est proposé. L’idée fondamentale est de grouper les états MMC en fonction des connaissances phonologiques et en se basant sur les données, pour ensuite associer chaque état avec un homologue phonologiquement cohérent dans une langue différente. Ce cadre est également utilisé lors de la construction d’un arbre de régression pour l’estimation des transformations. Il ressort que le cadre proposé atténue l’impact négatif de la disparité de langue, et conduit à une solide amélioration par rapport aux précédentes méthodes de l’état de l’art. Enfin, un cadre de transformation hiérarchique à deux couches est proposé, où une couche vise à capturer les caractéristiques de la voix d’un locuteur cible, et l’autre couche compense la disparité de langue. Une étude initiale a été menée afin de déterminer une méthode permettant de construire cette structure hiérarchique de transformations. Bien que les résultats préliminaires soient prometteurs, des investigations plus approfondies restent nécessaire pour confirmer la validité de cette approche. Mots-clés disparité de langue, correspondance d’états MMC, amélioration axée sur les données, hiérarchie d’adaptation à deux couches, adaptation interlinguale de locuteur, traduction de parole à parole, synthèse vocale en utilisant des MMCs (Translated by Laurent El Shafey as per the English version)

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis

A phone mapping-based method had been introduced for cross-lingual speaker adaptation in HMM-based speech synthesis. In this paper, we continue to propose a state mapping based method for cross-lingual speaker adaptation, where the state mapping between voice models in source and target languages is established under minimum Kullback-Leibler divergence (KLD) criterion. We introduce two approach...

متن کامل

Phonological Knowledge Guided HMM State Mapping for Cross-Lingual Speaker Adaptation

Within the HMM state mapping-based cross-lingual speaker adaptation framework, the minimum Kullback-Leibler divergence criterion has been typically employed to measure the similarity of two average voice state distributions from two respective languages for state mapping construction. Considering that this simple criterion doesn’t take any language-specific information into account, we propose ...

متن کامل

Enhancing State Mapping-based Cross-lingual Speaker Adaptation Using Phonological Knowledge in a Data-driven Manner

HMM state mapping with the Kullback-Leibler divergence as a distribution similarity measure is a simple and effective technique that enables cross-lingual speaker adaptation for speech synthesis. However, since this technique does not take any other potentially useful information into account for mapping construction, an approach involving phonological knowledge in a data-driven manner is propo...

متن کامل

Cross-lingual speaker adaptation via Gaussian component mapping

This paper is focused on the use of acoustic information from an existing source language (Cantonese) to implement speaker adaptation for a new target language (English). Speakerindependent (SI) model mapping between Cantonese and English is investigated at different levels of acoustic units. Phones, states, and Gaussian mixture components are used as the mapping units respectively. With the mo...

متن کامل

An analysis of language mismatch in HMM state mapping-based cross-lingual speaker adaptation

This paper provides an in-depth analysis of the impacts of language mismatch on the performance of cross-lingual speaker adaptation. Our work confirms the influence of language mismatch between average voice distributions for synthesis and for transform estimation and the necessity of eliminating this mismatch in order to effectively utilize multiple transforms for cross-lingual speaker adaptat...

متن کامل

Cross-Lingual Speaker Adaptation for Statistical Speech Synthesis Using Limited Data

Cross-lingual speaker adaptation with limited adaptation data has many applications such as use in speech-to-speech translation systems. Here, we focus on cross-lingual adaptation for statistical speech synthesis (SSS) systems using limited adaptation data. To that end, we propose two techniques exploiting a bilingual Turkish-English speech database that we collected. In one approach, speaker-s...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012