Existing standard speech coders can provide speech communication of high quality while they degrade the performance of speech recognition systems that use the reconstructed speech...
Compressed-domain automatic speaker recognition is based on the analysis of the compressed parameters of speech coders. The objective is to perform low-complexity on-line speaker ...
Matteo Petracca, Antonio Servetti, Juan Carlos De ...
Unit selection text-to-speech systems currently produce very natural synthesized phrases by concatenating speech segments from a large database. Recently, increasing demand for de...
This paper presents a corrective model for speech recognition of inflected languages. The model, based on a discriminative framework, incorporates word ngrams features as well as ...
The most popular model used in automatic speech recognition is the hidden Markov model (HMM). Though good performance has been obtained with such models there are well known limit...