✦ LIBER ✦

Minimum classification error rate methods for speech recognition

✍ Scribed by Biing-Hwang Juang, ; Wu Hou, ; Chin-Hui Lee,

Book ID: 119957076
Publisher: IEEE
Year: 1997
Tongue: English
Weight: 290 KB
Volume: 5
Category: Article
ISSN: 1063-6676
DOI: 10.1109/89.568732

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Discriminant-function-based minimum reco

Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition

✍ Wu Chou 📂 Article 📅 2000 🏛 IEEE 🌐 English ⚖ 357 KB

Prototype-based minimum error training f

Prototype-based minimum error training for speech recognition

✍ Erik McDermott; Shigeru Katagiri 📂 Article 📅 1994 🏛 Springer US 🌐 English ⚖ 976 KB

Correction to "discriminant-function-bas

Correction to "discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition"

✍ Wu Chou 📂 Article 📅 2000 🏛 IEEE 🌐 English ⚖ 5 KB

String-based minimum verification error

String-based minimum verification error (SB-MVE) training for speech recognition

✍ Mazin G. Rahim; Chin-Hui Lee 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 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

Minimum classification error training in

Minimum classification error training in example based speech and pattern recognition using sparse weight matrices

✍ Mike Matton; Dirk Van Compernolle; Ronald Cools 📂 Article 📅 2010 🏛 Elsevier Science 🌐 English ⚖ 370 KB

Prototype-based minimum classification e

Prototype-based minimum classification error/generalized probabilistic descent training for various speech units

✍ Erik McDermott; Shigeru Katagiri 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 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