Proceedings of the 4 th International Conference on NOn - LInear Speech Processing

نویسندگان

  • Xavi Gonzalvo
  • Ignasi Iriondo
  • Joan Claudi Socoró
  • Francesc Alías
  • Carlos Monzo
  • Mehmet Atas
  • Suleyman Baykut
  • Tayfun Akgul
  • Ufuk Ulug
  • Tolga Esat Ozkurt
چکیده

Hidden Markov Models based text-to-speech (HMM-TTS) synthesis is a technique for generating speech from trained statistical models where spectrum, pitch and durations of basic speech units are modelled altogether. The aim of this work is to describe a Spanish HMM-TTS system using CBR as a F0 estimator, analysing its performance objectively and subjectively. The experiments have been conducted on a reliable labelled speech corpus, whose units have been clustered using contextual factors according to the Spanish language. The results show that the CBR-based F0 estimation is capable of improving the HMM-based baseline performance when synthesizing nondeclarative short sentences and reduced contextual information is available.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Pragmatic Study of Speech Acts by Iranian and Spanish Nonnative English Learners

This study was an attempt to investigate Iranian and Spanish intermediate nonnative English learners’ request strategies to their faculty. To this aim, 74 (50 Iranian and 24 Spanish) nonnative English intermediate learners participated in this study. A discourse completion test (DCT) was used to elicit the request strategies used by the participants. The findings suggested the participants empl...

متن کامل

Requestive Speech Acts Realization Patterns: Observation from Persian

Without knowing the speech act functions, it would be difficult to make correct requests in a language. Studies in pragmalinguistics have shown that conventionally direct and indirect requestive patterns are perceived differently in different speech communities. This study investigates the perception of the requestive speech acts by Persian native speakers to determine the socially appropriate ...

متن کامل

The Function of Pitch Range Variations in Samples of Emotional Expressions in Persian

This study aims at investigating the interface between emotion and intonation patterns (more specifically, duration and pitch amplitude of speech). To this end, the acoustic properties of spectral parameters related to speech prosody are investigated. The results of acoustic and Statistical analysis show that mean level and range of FO in the contours vary strongly as a function of the degree o...

متن کامل

ذخیره 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 2007