In an effort to increase the naturalness of concatenative speech synthesis, large speech databases may be recorded. While it is desirable to have varied prosodic and spectral characteristics in the database, it is not desirable to have variable voice quality. In this paper we present an automatic method for voice quality assessment and correction, whenever necessary, of large speech databases f...

In recent years, IP telephone use has spread rapidly thanks to the development of VoIP (Voice over IP) technology. However, an unavoidable problem of the IP telephone is deterioration of speech due to packet loss, which often occurs on the wireless network. To overcome this problem, we propose a novel packet loss concealment algorithm using speech recognition and synthesis. This proposed method...

Substantial individual differences in speech perception emerge under adverse listening conditions, including when perceiving unfamiliar speech. In the present study, individual differences in word recognition for three varieties of unfamiliar speech—Spanish-accented English, Irish-accented English, and dysarthric speech—were investigated. We asked whether the ability to perceive these unfamilia...

This paper presents overview of an online audio indexing system, which creates a searchable index of speech content embedded in digitized audio files. This system is based on our recently proposed offline audio segmentation techniques. As the data arrives continuously, the system first finds boundaries of the acoustically homogenous segments. Next, each of these segments is classified as speech...

This paper introduces the architecture and interface of a serious game intended for pronunciation training and assessment for Spanish students of English as second language. Users will confront a challenge consisting in the pronunciation of a minimal-pair word battery. Android ASR and TTS tools will prove useful in discerning three different pronunciation proficiency levels, ranging from basic ...

Recently, an increasing attention has been paid to Mandarin word stress which is important for improving the naturalness of speech synthesis. Most of the research on Mandarin speech synthesis focuses on three stress levels: stressed, regular and unstressed. This paper emphasizes the unstressed syllable prediction because the unstressed syllable is also important to the intelligibility of the sy...

We present an improved algorithm for a robust speech analysissynthesis method based on an auto-regressive with exogenous input (ARX) speech production model proposed previously. The speech analysis-synthesis method is capable of making an automatic estimation of vocal tract (formant) and voice source parameters from a speech utterance, generating accurate formant values even for very high-pitch...

Within the research project SIMULEKT (Simulating Intonational Varieties of Swedish), our recent work includes two approaches to simulating intonation in regional varieties of Swedish. The first involves a method for modeling intonation using the SWING (SWedish INtonation Generator) tool, where annotated speech samples are resynthesised with rule-based intonation and audio-visually analysed with...

Within the research project SIMULEKT (Simulating Intonational Varieties of Swedish), our recent work includes two approaches to simulating intonation in regional varieties of Swedish. The first involves a method for modelling intonation using the SWING (SWedish INtonation Generator) tool, where annotated speech samples are resynthesised with rule-based intonation and audio-visually analysed wit...