Evaluation of the synthesis
Text-To-Speech synthesis
Article REF: H7288 V2
Evaluation of the synthesis
Text-To-Speech synthesis

Authors : Christophe D'ALESSANDRO, Gaël RICHARD

Publication date: November 10, 2013 | Lire en français

Logo Techniques de l'Ingenieur You do not have access to this resource.
Request your free trial access! Free trial

Already subscribed?

7. Evaluation of the synthesis

7.1 Black box or glass box

Synthesis evaluation is necessary to compare systems with each other and to measure progress. Evaluation of synthesis speech can be global (the signal generated) or focused on one aspect of the system.

Overall evaluation is generally that of the customer, who listens to and evaluates the synthesizer on the speech produced. Component evaluation is of more interest to the researcher or developer, who is looking to improve an aspect of the system.

Text-to-speech synthesis is a chain of processes, from text to acoustic signal. It is therefore the weakest link in the chain that will limit its quality, hence the importance of evaluating each module (analytical or internal evaluation, or "glass box"), in addition...

You do not have access to this resource.
Logo Techniques de l'Ingenieur

Exclusive to subscribers. 97% yet to be discovered!

You do not have access to this resource. Click here to request your free trial access!

Already subscribed?


Article included in this offer

"Digital documents and content management"

( 71 articles )

Complete knowledge base

Updated and enriched with articles validated by our scientific committees

Services

A set of exclusive tools to complement the resources

View offer details