Name
Abstract | ||
|---|---|---|
In the last years, support vector machines (SVMs) have shown excellent performance in many applications, especially in the presence of noise. In particular, SVMs offer several advantages over artificial neural networks (ANNs) that have attracted the attention of the speech processing community. Nevertheless, their high computational requirements prevent them from being used in practice in automatic speech recognition (ASR), where ANNs have proven to be successful. The high complexity of SVMs in this context arises from the use of huge speech training databases with millions of samples and highly overlapped classes. This paper suggests the use of a weighted least squares (WLS) training procedure that facilitates the possibility of imposing a compact semiparametric model on the SVM, which results in a dramatic complexity reduction. Such a complexity reduction with respect to conventional SVMs, which is between two and three orders of magnitude, allows the proposed hybrid WLS-SVC/HMM system to perform real-time speech decoding on a connected-digit recognition task (SpeechDat Spanish database). The experimental evaluation of the proposed system shows encouraging performance levels in clean and noisy conditions, although further improvements are required to reach the maturity level of current context-dependent HMM-based recognizers. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TASL.2011.2178597 | IEEE Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
artificial neural network,speech,real time systems,artificial neural networks,semiparametric model,context dependent,speech recognition,hidden markov models,speech processing,automatic speech recognition,complexity reduction,real time,speech coding,hidden markov model,machine learning,support vector machine,neural nets,support vector machines | Speech processing,Speech coding,Computer science,Semiparametric model,Artificial intelligence,Artificial neural network,Pattern recognition,Support vector machine,Speech recognition,Reduction (complexity),Decoding methods,Hidden Markov model,Machine learning | Journal |
Volume | Issue | ISSN |
20 | 4 | 1558-7916 |
Citations | PageRank | References |
8 | 0.49 | 40 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rubén Solera-Urena | 1 | 12 | 2.27 |
| Ana Isabel Garcia-Moral | 2 | 13 | 1.61 |
| Carmen Peláez-moreno | 3 | 130 | 22.07 |
| Manel Martínez-ramón | 4 | 216 | 19.66 |
| Fernando Díaz-de-María | 5 | 201 | 32.14 |