The SVOX Text-to-Speech System
نویسنده
چکیده
Since the automatic semantic and pragmatic analysis of arbitrary texts is far from being reality, general purpose TTS systems can rely on simpler knowledge only, in particular on syntactic and morphological language knowledge. Although, from a linguistic point of view, this way of proceeding is very rough, it delivers very often quite acceptable results, mainly because there is a strong relation between the syntactic structure and the semantic and pragmatic content of a text.
منابع مشابه
The Svox Text-to-speech System
This document gives an overview of the current state of the SVOX text-to-speech (TTS) system, which has been developed at TIK/ETHZ. Conceptual considerations Correctly reading aloud a text requires far more than word pronunciation knowledge. In general, complete understanding of the semantic content and of the pragmatic context is necessary, regardless of whether a human or a machine is reading...
متن کاملSVOX Participation in Blizzard 2007
This paper describes the SVOX system architecture and the steps we took to integrate the Blizzard database into our system. The results of the Blizzard evaluation show that SVOX is a leader in small and large footprint unit selection. Analysis of the mean opinion scores for specific sentences shows where our system can improve most. Some recommendations for future Blizzard Challenges are also m...
متن کاملEmploying Sentence Structure: Syntax Trees as Prosody Generators
In this paper, we describe a prosody generation system for speech synthesis that makes direct use of syntax trees to obtain duration and pitch. Instead of transforming the tree through special rules or extracting isolated features from the tree, we make use of the tree structure itself to construct a superpositional model that is able to learn the relation between syntax and prosody. We impleme...
متن کاملCipher text only attack on speech time scrambling systems using correction of audio spectrogram
Recently permutation multimedia ciphers were broken in a chosen-plaintext scenario. That attack models a very resourceful adversary which may not always be the case. To show insecurity of these ciphers, we present a cipher-text only attack on speech permutation ciphers. We show inherent redundancies of speech can pave the path for a successful cipher-text only attack. To that end, regularities ...
متن کاملSpoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting
Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIBchr('39')s archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1995