๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Prototype-based minimum error training for speech recognition

โœ Scribed by Erik McDermott; Shigeru Katagiri

Book ID
104985089
Publisher
Springer US
Year
1994
Tongue
English
Weight
976 KB
Volume
4
Category
Article
ISSN
0924-669X

No coin nor oath required. For personal study only.

๐Ÿ“œ SIMILAR VOLUMES

String-based minimum verification error
String-based minimum verification error (SB-MVE) training for speech recognition
โœ Mazin G. Rahim; Chin-Hui Lee ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 284 KB

In recent years, we have experienced an increasing demand for speech recognition technology to be utilized in various real-world applications, such as name dialling, message retrieval, etc. During this process, we have learned that the performance of speech recognition systems under laboratory envir

Prototype-based minimum classification e
Prototype-based minimum classification error/generalized probabilistic descent training for various speech units
โœ Erik McDermott; Shigeru Katagiri ๐Ÿ“‚ Article ๐Ÿ“… 1994 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 642 KB

In previous work we reported high classification rates for learning vector quantization (LVQ) networks trained to classify phoneme tokens shifted in time. It has since been shown that the framework of minimum classification error (MCE) and generalized probabilistic descent (GPD) can treat LVQ as a s