Prominences and boundaries are the essential constituents of prosodic structure in speech.
They provide for means to chunk the speech stream into linguistically relevant units by …

We propose a two-stage emotion-controllable text-to-speech (TTS) model that can increase
the diversity of intra-emotion variation and also preserve inter-emotion controllability in …

Unsupervised boundary detection and classification is both a theoretically interesting
question and an important challenge for speech technology. Theoretical interest lies in …

Prominences and boundaries are the essential constituents of prosodic structure in speech.
They provide for means to chunk the speech stream into linguistically relevant units by …

The motivation for this exploratory research project is twofold. First, there is the contrast
between the importance of certain phenomena in English spoken communication on the one …

Text-to-speech synthesis is a task that solves many real-world problems such as providing
speaking and reading ability to people who lack those capabilities. It is thus viewed mainly …

In this paper we examine prosodic and syntactic structures of spontaneous English speech.
By wavelet-based analysis, the prosodic structure of speech can be visually represented as …

Statistical parametric speech synthesis (SPSS) has seen improvements over recent years,
especially in terms of intelligibility. Synthetic speech is often clear and understandable, but it …

Statistical parametric speech synthesis technologies, such as HMM-based and DNN-based
ones, gain special attention from researchers because of their ability in generating speech in …

Text-to-speech (TTS) models aim to synthesize human-like speech including linguistic and
paralinguistic information. Current TTS models [1, 2] can synthesize understandable speech …