### Abstract

This paper presents novel architectures for linear-phase FIR digital filters using stochastic computing. Stochastic computing systems require fewer logic gates and are inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Compared to direct-form linear-phase FIR filters, linear-phase lattice filters require twice the number of multipliers but the same number of adders. The hardware complexities of stochastic implementations of linear-phase FIR filters for direct-form and lattice structures are comparable. This is because multipliers do not require any more area than adders. Two stochastic implementations of lattice FIR filters are proposed in this paper. Using speech signals from ICA ’99 Synthetic Benchmarks, it is shown that, for linear-phase FIR filters, the signal-to-error ratios of stochastic direct-form and stochastic lattice filters are abou the same.

Original language | English (US) |
---|---|

Pages (from-to) | 791-803 |

Number of pages | 13 |

Journal | Journal of Signal Processing Systems |

Volume | 90 |

Issue number | 5 |

DOIs | |

State | Published - May 1 2018 |

### Fingerprint

### Keywords

- FIR digital filter
- Fault-tolerance
- Hardware complexity
- Lattice structure
- Linear-phase FIR filters
- Stochastic computing
- Stochastic logic

### Cite this

**Linear-Phase Lattice FIR Digital Filter Architectures Using Stochastic Logic.** / Liu, Yin; Parhi, Keshab K.

Research output: Contribution to journal › Article

*Journal of Signal Processing Systems*, vol. 90, no. 5, pp. 791-803. https://doi.org/10.1007/s11265-017-1224-z

}

TY - JOUR

T1 - Linear-Phase Lattice FIR Digital Filter Architectures Using Stochastic Logic

AU - Liu, Yin

AU - Parhi, Keshab K

PY - 2018/5/1

Y1 - 2018/5/1

N2 - This paper presents novel architectures for linear-phase FIR digital filters using stochastic computing. Stochastic computing systems require fewer logic gates and are inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Compared to direct-form linear-phase FIR filters, linear-phase lattice filters require twice the number of multipliers but the same number of adders. The hardware complexities of stochastic implementations of linear-phase FIR filters for direct-form and lattice structures are comparable. This is because multipliers do not require any more area than adders. Two stochastic implementations of lattice FIR filters are proposed in this paper. Using speech signals from ICA ’99 Synthetic Benchmarks, it is shown that, for linear-phase FIR filters, the signal-to-error ratios of stochastic direct-form and stochastic lattice filters are abou the same.

AB - This paper presents novel architectures for linear-phase FIR digital filters using stochastic computing. Stochastic computing systems require fewer logic gates and are inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Compared to direct-form linear-phase FIR filters, linear-phase lattice filters require twice the number of multipliers but the same number of adders. The hardware complexities of stochastic implementations of linear-phase FIR filters for direct-form and lattice structures are comparable. This is because multipliers do not require any more area than adders. Two stochastic implementations of lattice FIR filters are proposed in this paper. Using speech signals from ICA ’99 Synthetic Benchmarks, it is shown that, for linear-phase FIR filters, the signal-to-error ratios of stochastic direct-form and stochastic lattice filters are abou the same.

KW - FIR digital filter

KW - Fault-tolerance

KW - Hardware complexity

KW - Lattice structure

KW - Linear-phase FIR filters

KW - Stochastic computing

KW - Stochastic logic

UR - http://www.scopus.com/inward/record.url?scp=85010764285&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010764285&partnerID=8YFLogxK

U2 - 10.1007/s11265-017-1224-z

DO - 10.1007/s11265-017-1224-z

M3 - Article

AN - SCOPUS:85010764285

VL - 90

SP - 791

EP - 803

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

SN - 1939-8018

IS - 5

ER -