Adaptation de la prononciation pour la synthèse de la parole spontanée en utilisant des informations linguistiques
Abstract
This paper presents a new pronunciation adaptation method which adapts canonical pronunciations
to a spontaneous style. This is a key task in text-to-speech as those pronunciation variants bring
expressiveness to synthetic speech, thus enabling new potential applications. The strength of the
method is to solely rely on linguistic features and to consider a probabilistic machine learning
framework, namely conditional random fields, to produce the adapted pronunciations. Features are
selected in a first series of experiments, then combined in the backend experiments. Results on the
Buckeye conversational English speech corpus show that adapted pronunciations significantly better
reflect spontaneous speech than canonical ones.
Cet article présente une nouvelle méthode d'adaptation de la prononciation dont le but est de reproduire le style spontané. Il s'agit d'une tâche-clé en synthèse de la parole car elle permet d'apporter de l'expressivité aux signaux produits, ouvrant ainsi la voie à de nouvelles applications. La force de la méthode proposée est de ne s'appuyer que sur des informations linguistiques et de considérer un cadre probabiliste pour ce faire, précisément les champs aléatoires conditionnels. Dans cet article, nous étudions tout d'abord la pertinence d'un ensemble d'informations pour l'adaptation, puis nous combinons les informations les plus pertinentes lors d'expériences finales. Les évaluations de la méthode sur un corpus de parole conversationnelle en anglais montrent que les prononciations adaptées reflètent significativement mieux un style spontané que les prononciations canoniques. ABSTRACT Pronunciation adaptation for spontaneous speech synthesis using linguistic information. This paper presents a new pronunciation adaptation method which adapts canonical pronunciations to a spontaneous style. This is a key task in text-to-speech as those pronunciation variants bring expressiveness to synthetic speech, thus enabling new potential applications. The strength of the method is to solely rely on linguistic features and to consider a probabilistic machine learning framework, namely conditional random fields, to produce the adapted pronunciations. Features are selected in a first series of experiments, then combined in the backend experiments. Results on the Buckeye conversational English speech corpus show that adapted pronunciations significantly better reflect spontaneous speech than canonical ones. MOTS-CLÉS : Adaptation de la prononciation, parole spontanée, synthèse de la parole.
Origin | Files produced by the author(s) |
---|
Loading...