✦ LIBER ✦

Unsupervised training of acoustic models for large vocabulary continuous speech recognition

✍ Scribed by Wessel, F.; Ney, H.

Book ID: 117935912
Publisher: IEEE
Year: 2005
Tongue: English
Weight: 479 KB
Volume: 13
Category: Article
ISSN: 1063-6676
DOI: 10.1109/tsa.2004.838537

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Boosting systems for large vocabulary co

Boosting systems for large vocabulary continuous speech recognition

✍ George Saon; Hagen Soltau 📂 Article 📅 2012 🏛 Elsevier Science 🌐 English ⚖ 301 KB

Combining Spectral Representations for L

Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition

✍ Garau, G.; Renals, S. 📂 Article 📅 2008 🏛 Institute of Electrical and Electronics Engineers 🌐 English ⚖ 740 KB

A fast approximate acoustic match for la

A fast approximate acoustic match for large vocabulary speech recognition

✍ Bahl, L.R.; De Gennaro, S.V.; Gopalakrishnan, P.S.; Mercer, R.L. 📂 Article 📅 1993 🏛 IEEE 🌐 English ⚖ 913 KB

Lattice segmentation and minimum Bayes r

Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition

✍ Vlasios Doumpiotis; William Byrne 📂 Article 📅 2006 🏛 Elsevier Science 🌐 English ⚖ 263 KB

A word graph algorithm for large vocabul

A word graph algorithm for large vocabulary continuous speech recognition

✍ Stefan Ortmanns; Hermann Ney; Xavier Aubert 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 360 KB

This paper describes a method for the construction of a word graph (or lattice) for large vocabulary, continuous speech recognition. The advantage of a word graph is that a fairly good degree of decoupling between acoustic recognition at the 10-ms level and the final search at the word level using a

An overview of decoding techniques for l

An overview of decoding techniques for large vocabulary continuous speech recognition

✍ Xavier L. Aubert 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 351 KB

A number of decoding strategies for large vocabulary continuous speech recognition (LVCSR) are examined from the viewpoint of their search space representation. Different design solutions are compared with respect to the integration of linguistic and acoustic constraints, as implied by m-gram langua