Paraphrase generation to improve text-to-speech synthesis
نویسندگان
چکیده
Text-to-speech synthesizer systems are of overall good quality, especially when adapted to a specific task. Given this task and an adapted voice corpus, the message quality is mainly dependent on the wording used. This paper presents how a paraphrase generator can be used in synergy with a text-to-speech (TTS) synthesis system to improve its overall performances. Our system is composed of a paraphrase generator using a French-toFrench corpus learnt on a bilingual aligned corpus, a TTS selector based on the unit selection cost, and a TTS synthesizer. We present an evaluation of the system, which highlights the need for systematic subjective evaluation.
منابع مشابه
Study on Unit-Selection and Statistical Parametric Speech Synthesis Techniques
One of the interesting topics on multimedia domain is concerned with empowering computer in order to speech production. Speech synthesis is granting human abilities to the computer for speech production. Data-based approach and process-based approach are the two main approaches on speech synthesis. Each approach has its varied challenges. Unit-selection speech synthesis and statistical parametr...
متن کاملUsing Multiple Metrics in Automatically Building Turkish Paraphrase Corpus
Paraphrasing is expressing similar meanings with different words in different order. In this sense it is viewed as translation in the same language. It is an important issue in natural language processing for automatic machine translation, question answering, text summarization and language generation. Studies in paraphrasing can be classified as paraphrase extraction, paraphrase generation, pa...
متن کاملUsing Dependency-Based Features to Take the 'Para-farce' out of Paraphrase
As research in text-to-text paraphrase generation progresses, it has the potential to improve the quality of generated text. However, the use of paraphrase generation methods creates a secondary problem. We must ensure that generated novel sentences are not inconsistent with the text from which it was generated. We propose a machine learning approach be used to filter out inconsistent novel sen...
متن کاملمراحل و نحوه ی تهیه ی دادگان های صوتی هجایی و دایفونی برای سامانه ی تبدیل متن به گفتار فارسی
Abstract Speech databases are part of the concatenative text to speech synthesis systems. Phonetic quality of the databases plays a significant role in the naturalness of the synthesized speech. This paper introduces two syllable and diphone speech databases for Persian and investigates the way of their development and their specifications and their advantages to each other. ...
متن کاملOn the use of automatically generated discourse-level information in a concept-to-speech synthesis system
This paper describes the latest version of the SOLE concept-tospeech system, which uses linguistic information provided by a natural language generation system to improve the prosody of synthetic speech. We discuss the types of linguistic information that prove most useful and the implications for text-to-speech systems.
متن کامل