Abstract | ||
---|---|---|
A speaker-independent isolated word recognition system is described which is based on some techniques and results from rate-distortion speech coders. The recognition system can be viewed as a minimum distortion or nearest-neighbor system where the distortion measure is defined between an observed sequence of frames of speech and a reference pattern. The patterns are sequences of sets of LPC models. Every one of the sets of each pattern consist of a collection of LPC models that "best" reproduces a given frame of a word from a training sequence. The Itakura Saito distortion measure is used to design the system (or selection of the patterns) and for the decision step. |
Year | DOI | Venue |
---|---|---|
1982 | 10.1109/ICASSP.1982.1171772 | Acoustics, Speech, and Signal Processing, IEEE International Conference ICASSP '82. |
Keywords | Field | DocType |
source coding,word recognition,linear predictive coding,noise measurement,speech coding,encoding,digital filters,source code,nearest neighbor,dictionaries | Speech enhancement,Speech coding,Pattern recognition,Voice activity detection,Computer science,Word recognition,Speech recognition,Artificial intelligence,Shannon–Fano coding,Distortion,Linear predictive coding,Variable-length code | Conference |
Volume | Citations | PageRank |
7 | 9 | 19.70 |
References | Authors | |
1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andres Buzo | 1 | 9 | 19.70 |
Horacio G. Martinez | 2 | 9 | 19.70 |
Carlos Rivera | 3 | 10 | 20.47 |