Foreword Modification of Speech: Tribute to Mike Macon

Modification of Speech: a Tribute to Mike Macon

This paper provides an overview of, and puts in perspective, the contributions of Mike Macon to text-to-speech synthesis (TTS). The core of his work consists of signal processing algorithms that modify speech. The paper argues that major opportunities exist for TTS systems that modify prosody of acoustic units, instead of searching for units having the required prosody. However, the challenges ...

Festival speaks Italian!

Finally Festival speaks Italian. In this work, the development of the first Italian version of the Festival TTS system is described. One male and one female voice for three different speech engines are considered: the Festival-specific residual LPC synthesizer, the OGI residual LPC Plug-In for Festival and the MBROLA synthesizer. The new Italian voices will be freely available for download for ...

Sinusoidal modeling and modification of unvoiced speech

Synthesis of prosody using multi-level unit sequences

Generating meaningful and natural sounding prosody is a central challenge in textto-speech synthesis (TTS). In traditional synthesis, the challenge consists of how to generate natural target prosodic contours and how to impose these contours on recorded speech without causing audible distortions. In unit selection synthesis, the challenge is the sheer size of the speech corpus that is needed to...

Spectral modification for concatenative speech synthesis

Concatenative synthesis can produce high-quality speech but is limited to the allophonic variations and voice types that were captured in the database. It would be desirable to modify speech units to remove formant discontinuities and to create new speaking styles, such as hypoor hyper-articulated speech. Unfortunately, manipulating the spectral structure often leads to degraded speech quality....