Title | ||
---|---|---|
Robust speech recognition using improved vector taylor series algorithm for embedded systems |
Abstract | ||
---|---|---|
This paper proposes a novel robust speech recognition technique using improved vector Taylor series (VTS) algorithm for embedded systems. It uses a hidden Markov model (HMM) to replace the Gaussian mixture model (GMM) for estimating the clean speech feature, and gives the closed-form solutions of the noise parameters including the mean and variance at each expectation-maximization (EM) iteration. The experimental results show that the proposed algorithm makes a good balance between the computational complexity and recognition accuracy, and thus is more useful for embedded systems. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/TCE.2010.5505999 | Consumer Electronics, IEEE Transactions |
Keywords | Field | DocType |
Robust speech recognition, vector Taylor series, feature compensation, hidden Markov model | Pattern recognition,Computer science,Iterative method,Algorithm,Speech recognition,Artificial intelligence,Feature compensation,Hidden Markov model,Mixture model,Taylor series,Embedded system,Computational complexity theory | Journal |
Volume | Issue | ISSN |
56 | 2 | 0098-3063 |
Citations | PageRank | References |
1 | 0.37 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yong Lü | 1 | 1 | 0.37 |
Haiyang Wu | 2 | 28 | 5.99 |
Zhenyang Wu | 3 | 154 | 17.52 |