Synthesis and evaluation of intonation with a superposition model
نویسندگان
چکیده
A data-driven method based on a new paradigm is introduced in this paper. We assume that cognitive representations of the discourse are prosodically encoded by means of global multiparametric prototypes. The generation of adequate prosodic contours is then obtained by retrieving and combining these elementary prototypic contours accessed by linguistic or paralinguistic keys. We examine here F0 generation. Two procedures have been applied: the first consists of a superposition model via a structured lexicon, the second uses a recurrent neural network. Preliminary experiments shows that both methods can lead to good quality F0 contours.
منابع مشابه
Generating German intonation with a trainable prosodic model
A trainable prosodic model called SFC (Superposition of Functional Contours), proposed by Holm and Bailly, is here confronted to German intonation. Training material is the publicly available Siemens Synthesis Corpus that provides spoken utterances for high-quality speech synthesis. We describe the labeling framework and first evaluation results that compares the original prosody of test senten...
متن کاملGenerating German intonation with
A trainable prosodic model called SFC (Superposition of Functional Contours), proposed by Holm and Bailly, is here confronted to German intonation. Training material is the publicly available Siemens Synthesis Corpus that provides spoken utterances for high-quality speech synthesis. We describe the labeling framework and first evaluation results that compares the original prosody of test senten...
متن کاملJapanese intonation synthesis using superposition and linear alignment models
This paper outlines a new approach to Tokyo Japanese intonation synthesis, in which the F0 contour of an utterance is generated using the superposition of multi-level phrase curves and lexical accent curves, coupled with linear alignment models which determine the precise alignment of the curves with the segmental material. We first discuss the construction of a phrase curve used to model the p...
متن کاملAutomatisation of intonation modelling and its linguistic anchoring
This paper presents a fully machine-driven approach for intonation description and its linguistic interpretation. For this purpose, a new intonation model for bottom-up F0 contour analysis and synthesis is introduced, the CoPaSul model which is designed in the tradition of parametric, contour-based, and superpositional approaches. Intonation is represented by a superposition of global and local...
متن کاملGenerating Spanish intonation with a trainable prosodic model
A trainable prosodic model called SFC (Superposition of Functional Contours), proposed by Holm and Bailly, is here applied to Castillan intonation. Training material has been kindly provided by the Speech Processing Group at UPC. We describe the labeling framework and first evaluation results that compares the original prosody of test sentences of this corpus with their prosodic rendering by th...
متن کامل