Paper Info
Title
The Nemours Database Of Dysarthric Speech
Abstract
The Nemours database is a collection of 814 short nonsense sentences; 74 sentences spoken by each of 11 male speakers with varying degrees of dysarthria Additionally, the database contains two connected-speech paragraphs produced by each of the 11 speakers. The database was designed to test the intelligibility of dysarthric speech before and after enhancement by various signal processing methods, and is available on CD-ROM. It can also be used to investigate general characteristics of dysarthric speech such as production error patterns. The entire database has been marked at the word level and sentences for 10 of the 11 talkers have been marked at the phoneme level as well. This paper describes the database structure and techniques adopted to improve the performance of a Discrete Hidden Markov Model (DHMM) labeler used to assign initial phoneme labels to the elements of the database. These techniques may be useful in the design of automatic recognition systems for persons with speech disorders, especially when limited amounts of training data an available.
Year
DOI
Venue
1996
10.1109/ICSLP.1996.608020
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4
Keywords
Field
DocType
speech processing,testing,databases,hidden markov model,signal processing,speech intelligibility,speech,speech recognition,hidden markov models,cd roms,training data,cd rom,automatic speech recognition
Speech enhancement,Dysarthric speech,Speech processing,Computer science,Artificial intelligence,Natural language processing,Database structure,Dysarthria,Intelligibility (communication),Training set,Speech recognition,Hidden Markov model,Database
Conference
Citations 
PageRank 
References 
45
5.23
0
Authors
5
Name
Order
Citations
PageRank
Xavier Menéndez-Pidal16210.26
James Polikoff27510.17
Shirley M. Peters3455.23
Jennie E. Leonzio4455.23
H. Timothy Bunnell511219.91