Current approaches to statistical parametric speech synthesis using Neural Networks generally require input at the same temporal resolution as the output, typically a frame every 5ms, or in some cases at waveform sampling rate. It is therefore necessary to fabricate highly-redundant frame-level (or samplelevel) linguistic features at the input. This paper proposes the use of a hierarchical enco...

This article analyzes the written expression in WhatsApp-type instant messaging applications of Andalusian adolescents who are last years compulsory education Spain. It aims to establish relationship between most relevant characteristics digital norm used by their communications through WhatsApp and dialectal variety Spanish. Additionally, this study intends determine whether writing influences...

The paper concerns universal and language-specific aspects of emotion perception in children's speech. Three experiments were carried out to investigate differences and similarities in the assessment of emotions by German and Russian adult listeners. The corpora of German and Russian emotional children's speech were employed in the first and second experiments. In the third experiment German an...

The Prosody-Voice Screening Pro® le (PVSP) is a clinical research instrument that quanti® es a speaker’ s conversational speech status in seven suprasegmental domains: phrasing, rate, stress, loudness, pitch, laryngeal quality and resonance. The PVSP has been used to assess the prosody-voice characteristics of children and adult speakers with typical speech-language development and with a varie...

This paper presents a brand-new Slovak text-to-speech system. It was developed within the framework of ARTIC system (primarily designed to synthesize Czech speech) with respect to the knowledge of Slovak language. Thus, statistical approach (using hidden Markov models) was employed to build an acoustic unit inventory of Slovak language in a fully automatic way. Both phonetic transcription and p...

Automatic recognition of syllables is useful for many spoken language applications such as speech recognition and spoken document retrieval. Short-term spectral properties (such as melfrequency cepstral coefficients, or MFCCs) are usually the features of choice for such systems, which typically ignore suprasegmental (prosodic) cues that manifest themselves at the syllable, word and utterance le...

This paper explores conversational grunts in a face-to-face setting. The study investigates the prosody and turn-taking effect of fillers and feedback tokens that has been annotated for attitudes. The grunts were selected from the DEAL corpus and automatically annotated for their turn taking effect. A novel suprasegmental prosodic signal representation and contextual timing features are used fo...

There are several possible situations in which perpetrators might want to disguise their voices in order to avoid identification and to deflect the search for them to another person or group of individuals. One possible manner that can be used for voice disguise is the adoption of another accent. This paper examines the mimicking of the British-English Swedish accent, that is mimicking of the S...

We introduce a new version of the pronunciation software program WinPitch LTL. This completely redesigned version is much more easier to use by the teacher and learner alike, and contains the regular function of prosodic real time display, variable speed playback, prosodic morphing, on screen teacher comment display, etc. New features include video capabilities (the program can process multimed...