Abstract | ||
---|---|---|
In this paper we present preliminary results obtained at Dragon Systems on the Resource Management benchmark task. The basic conceptual units of our system are Phonemes-in-Context (PICs), which are represented as Hidden Markov Models, each of which is expressed as a sequence of Phonetic Elements (PELs). The PELs corresponding to a given phoneme constitute a kind of alphabet for the representation of PICs.For the speaker-dependent tests, two basic methods of training the acoustic models were investigated. The first method of training the Resource Management models is to re-estimate the models for each test speaker from that speaker's training data, keeping the PEL spellings of the PICs fixed. The second approach is to use the re-estimated models from the first method to derive a segmentation of the training data, then to respell the PICs in a largely speaker-dependent manner in order to improve the representation of speaker differences. A full explanation of these methods is given, as are results using each method.In addition to reporting on two different training strategies, we discuss N-Best results. The N-Best algorithm is a modification of the algorithm proposed by Soong and Huang at the June 1990 workshop. This algorithm runs as a post-processing step and uses an A*-search (an algorithm also known as a 'stack decoder'). |
Year | DOI | Venue |
---|---|---|
1991 | 10.3115/112405.112412 | HLT |
Keywords | DocType | Citations |
benchmark result,resource management model,training data,basic conceptual unit,speaker difference,n-best algorithm,dragon systems resource management,different training strategy,basic method,resource management benchmark task,test speaker,n-best result,resource manager | Conference | 3 |
PageRank | References | Authors |
1.38 | 5 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
James Baker | 1 | 66 | 15.44 |
Janet Baker | 2 | 29 | 13.90 |
Paul Bamberg | 3 | 40 | 25.80 |
Larry Gillick | 4 | 89 | 32.78 |
L. Lamel | 5 | 2135 | 361.63 |
Robert Roth | 6 | 46 | 27.12 |
Francesco Scattone | 7 | 65 | 15.63 |
Dean Sturtevant | 8 | 91 | 37.38 |
Ousmane Ba | 9 | 3 | 1.38 |
Richard Benedict | 10 | 3 | 1.38 |