Evaluation of Lithuanian Text-to-Speech Synthesizers
نویسندگان
چکیده
منابع مشابه
Speech Synthesizers and Automatic Text - to - Speech Synthesis
4.1.1 Against the “toothpaste” metaphor Speech synthesis is often seen by engineers as an easy task, compared to speech recognition. It is true, indeed, that it is easier to create a bad, first trial text-to-speech (TTS) system than to design a rudimentary speech recognizer. After all, recording numbers up to 60 and a few words (“it is now”, “am”, “pm”) and being able to play them back in a giv...
متن کاملIncreasing prosodic variability of text-to-speech synthesizers
The lack of prosody variation in text-to-speech systems contributes to their perceived unnaturalness when synthesizing extended passages. In this paper, we present a method to improve prosody generation in this direction. A database of natural sample sentences is searched for sentences having similar word and syllable structure to the input. One sentence is selected randomly from the similar se...
متن کاملDiphone Databases for Lithuanian Text-to-Speech Synthesis
One of the components of the text-to-speech synthesis system is the database of sounds. Two Lithuanian diphone databases in the MBROLA format are presented in this paper. The list of phonemes and the list of diphones necessary for Lithuanian text-to-speech synthesis are described. The problem of phoneme combinations that are not used in the Lithuanian language is dealt with in the work. Also, t...
متن کاملAn Empirical Text Tranformation Method for Spontaneous Speech Synthesizers
The Fillers Inventory and Models block expands this scope of conventional text analysis. It facilitates the inclusion of spontaneous speech features, which would be later synthesized, during waveform generation. It is assumed during text analysis that the corresponding inventory of spontaneous speech features is available for waveform generation. The required Text Analysis/transformation perfor...
متن کاملAn empirical text transformation method for spontaneous speech synthesizers
The Fillers Inventory and Models block expands this scope of conventional text analysis. It facilitates the inclusion of spontaneous speech features, which would be later synthesized, during waveform generation. It is assumed during text analysis that the corresponding inventory of spontaneous speech features is available for waveform generation. The required Text Analysis/transformation perfor...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Studies About Languages
سال: 2016
ISSN: 2029-7203,1648-2824
DOI: 10.5755/j01.sal.0.28.15130