Title | ||
---|---|---|
Energy-Efficient Floating-Point MFCC Extraction Architecture for Speech Recognition Systems |
Abstract | ||
---|---|---|
This brief presents an energy-efficient architecture to extract mel-frequency cepstrum coefficients (MFCCs) for real-time speech recognition systems. Based on the algorithmic property of MFCC feature extraction, the architecture is designed with floating-point arithmetic units to cover a wide dynamic range with a small bit-width. Moreover, various operations required in the MFCC extraction are examined to optimize operational bit-width and lookup tables needed to compute nonlinear functions, such as trigonometric and logarithmic functions. In addition, the dataflow of MFCC extraction is tailored to minimize the computation time. As a result, the energy consumption is considerably reduced compared with previous MFCC extraction systems. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TVLSI.2015.2413454 | VLSI) Systems, IEEE Transactions |
Keywords | Field | DocType |
floating-point operations,hardware optimization,mel-frequency cepstrum coefficients (mfccs),speech recognition.,feature extraction,speech recognition,hardware,mel frequency cepstral coefficient | Lookup table,Mel-frequency cepstrum,Pattern recognition,Efficient energy use,Computer science,Floating point,Cepstrum,Feature extraction,Speech recognition,Dataflow,Artificial intelligence,Energy consumption | Journal |
Volume | Issue | ISSN |
PP | 99 | 1063-8210 |
Citations | PageRank | References |
4 | 0.51 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jihyuck Jo | 1 | 25 | 3.72 |
Hoyoung Yoo | 2 | 75 | 9.99 |
In-Cheol Park | 3 | 888 | 124.36 |