The paper presents a prosody adaptation method which is able to adapt the prosody model of text to speech (TTS) to a new style with a small training corpus. Unlike the conventional prosody mapping between two parallel prosody features, the paper tries to integrate the prosody conversion into the prosody generation model of TTS. In the paper, we use a template based prosody model which consists ...

the link between studies in discourse analysis and corpus linguistics has created new fields of research previously unattended. one of these areas is the study of semantic prosody produced through frequent collocation of a lexical item with a collection of words. semantic prosody is the positive, negative or neutral shade of meaning which a seemingly neutral word adopts after frequent collocati...

Recent work has shown that lexical items come to take on the phonetic characteristics of prosodic environments in which they are typically produced, a phenomenon referred as "leaky prosody". Focusing pitch patterns Mandarin, we show leaky prosody can be derived from flat (i.e., non-transformational, non-optimizing) model speech production. Formalized using Dynamic Field Theory, our model, lexic...

Abstract Rolle (2020) identifies an apparent morphophonological conspiracy in serial verb constructions (SVCs) Degema. He argues that it constitutes evidence for a partly-unified postsyntactic module, which morphology and prosody are built parallel (by ‘Optimality-Theoretic Distributed Morphology’). We argue the pattern Degema SVCs instead results from simultaneous interaction of two independen...

Research on the acoustic characteristics of Infant Directed Speech (IDS) in North American English indicates that it is generally higher-pitched than Adult (ADS) and has unique prosodic characteristics, which commonly found across many spoken languages. However, very little research addressed another important aspect prosody: voice quality. In current study, 25 English-speaking mothers from Can...

This paper proposes an approach to automatically evaluate the prosody of Chinese Mandarin speech for language learning. In this approach, we grade the appropriateness of prosody of speech units according to a model speech corpus from a teacher’s voice. To this end, we build two models, which are the prosody model and the scoring model. The prosody model that is built from the teacher’s speech p...

The current study had two main goals: First, to replicate the ‘bimodal integration’ effect (i.e. automatic integration of crossmodal stimuli, namely facial emotions and emotional prosody); second, investigate whether this phenomenon facilitates or impairs intake retention unattended verbal content. borrowed from previous bimodal designs included a two-alternative forced-choice (2AFC) task, wher...

BACKGROUND Parkinson's disease (PD) provides a model for investigating the involvement of the basal ganglia and mesolimbic dopaminergic system in the recognition of emotions from voices (i.e., emotional prosody). Although previous studies of emotional prosody recognition in PD have reported evidence of impairment, none of them compared PD patients at different stages of the disease, or ON and O...