A Self-learning Speech Synthesis System

نویسنده

  • C. S. Blackburn
چکیده

We describe a self-organising pseudo-articulatory speech production model (SPM), and present recent results when training the system on an X-ray mi-crobeam database. The SPM extracts statistics describing articulator positions and curvatures during the production of continuous speech, then applies an explicit co-articulation model to generate synthetic articulator trajectories corresponding to time-aligned phonemic strings. A set of artiicial neural networks estimates parameterised speech vectors from the synthetic articulator traces. We present an analysis of the articulatory information in the X-ray microbeam database used, and demonstrate the improvements in articulatory and acoustic modelling accuracy obtained using our co-articulation system. Nous d ecrivons un mod ele auto-organisatif pseudo-articulatoire de la production de la parole (SPM), et pr esentons des r esultats obtenus sur une base de donn ees contenant de micro-faisceaux de rayons X. Le SPM extrait des statistiques d ecrivant les positions et courbures des articulateurs lors de la production de la parole continue, puis met en application un mod ele explicite de la co-articulation pour g en erer des trajectoires articulatoires synth etiques qui s'accordent avec une s equence de phon emes align e dans le temps. Un ensemble de r eseaux neuromim etiques estime les vecteurs param etriques de la parole en fonction des traces synth etiques artic-ulatoires. Nous pr esentons une analyse du contenu informationnel de la base de donn ees utilis ee, et montrons l'am elioration des mod eles articulatoires et acoustiques obtenu en utilisant notre syst eme co-articulatoire.

برای دانلود 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

An Analysis of Self-Regulatory Learning Strategies in Secondary School Blended Learning Atmospheres: A Synthesis Research

This synthesis research has aimed to identify the features of blended learning environments which support self-regulatory learning strategies in high school students. The statistical population was derived from five foreign databases, consisting of 128 articles from 2017 to 2020. The data obtained were integrated using Sandelowski & Barroso's meta-synthesis method (2005). STROBE Checklist was u...

متن کامل

Combined Gesture-Speech Recognition and Synthesis Using Neural Networks

Sign languages such as Spanish Sign Language (LSE) are the primary communication way among members of the Deaf community. However this language is not widely known outside of this community. The techniques for automatic recognizing hand signs proposed in this paper allow creating systems which can help deaf people to communicate with others, by providing them with computer tools for assisted co...

متن کامل

Data-driven approaches for automatic detection of syllable boundaries

Syllabification is an essential component of many speech and language processing systems. The development of automatic speech recognizers frequently requires working with subword units such as syllables. More importantly, syllabification is an inevitable part of speech synthesis system. In this paper we present data-driven approaches to supervised learning and automatic detection of syllable bo...

متن کامل

مقایسه روش‌های مختلف یادگیری ماشین در خلاصه‌سازی استخراجی گفتار به گفتار فارسی بدون استفاده از رونوشت

In this paper, extractive speech summarization using different machine learning algorithms was investigated. The task of Speech summarization deals with extracting important and salient segments from speech in order to access, search, extract and browse speech files easier and in a less costly manner. In this paper, a new method for speech summarization without using automatic speech recognitio...

متن کامل

Perspectives for articulatory speech synthesis

Articulatory speech synthesis currently has two perspectives. (i) Technical perspective: Due to progress in common computer hardware (general increase in computation rate) and software (usability of compilers and simulation software) it is now possible to develop comprehensive phonetic models of speech production reaching nearly real-time for the calculation of acoustic speech signals. Furtherm...

متن کامل

Design and Implementation of an Intelligent Part of Speech Generator

The aim of this paper is to report on an attempt to design and implement an intelligent system capable of generating the correct part of speech for a given sentence while the sentence is totally new to the system and not stored in any database available to the system. It follows the same steps a normal individual does to provide the correct parts of speech using a natural language processor. It...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996