LMS-Based Algorithms with Multi-Band Decomposition of the Estimation Error Applied to System Identification (Special Section on Digital Signal Processing)
スポンサーリンク
概要
- 論文の詳細を見る
A new cost function based on multi-band decomposition of the estimation error and application of a different step-size for each band is used in connection with the least-mean-square criterion to improve the fidelity of estimates as compared to those obtained with conventional least-mean-square adaptive algorithms. The basic new idea is to trade off time and frequency resolutions of the adaptive algorithm along the frequency domain by using different step-sizes in the analysis of distinct frequencies in accordance with the frequency-localized statistical behavior of the input signal. The mathematical background for a stochastic approach to the multi-band decomposition-based scheme is presented and algorithms with fixed and variable step-sizes are derived. Computer experiments compare the performance of multi-band and conventional least-mean-square methods when applied to system identification.
- 社団法人電子情報通信学会の論文
- 1997-08-25
著者
-
Resende F
Tokyo Inst. Technol. Tokyo Jpn
-
Kaneko M
Japan Advanced Inst. Sci. And Technol. Jpn
-
Kaneko Mineo
School Of Information Science Japan Advanced Institute Of Science And Technology
-
Tokuda K
Department Of Computer Science And Engineering Nagoya Institute Of Technology
-
Tokuda Keiichi
Department Of Computer Science And Engineering Nagoya Institute Of Technology
-
Tokuda Keiichi
Ee
-
RESENDE Fernando
Department of Electronics and Computer Science
-
NISHIHARA Akinori
Department of Physical Electronics, Faculty of Engineering, Tokyo Institute of Technology
-
Tokuda Keiichi
The Department Of Computer Science Nagoya Institute Of Technology
-
Kaneko Mineo
Federal University Of Rio De Janeiro
-
Nishihara A
Tokyo Inst. Technol. Tokyo Jpn
-
DINIZ Paulo
Prog. de Engenharia Eletrica e Depto. de Eletronica, COPPE
-
Diniz Paulo
Prog. De Engenharia Eletrica E Depto. De Eletronica Coppe
-
Nishihara Akinori
Center For Research And Development Of Educational Technology Tokyo Institute Of Technology
-
Nishihara Akinori
Department Communications And Integrated Systems Tokyo Institute Of Technology
関連論文
- Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005(Speech and Herring)
- Applying Sparse KPCA for Feature Extraction in Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- On the Use of Kernel PCA for Feature Extraction in Speech Recognition(Speech and Hearing)
- Design Method for 2-Channel Signal Word Decomposed Filters with Minimum Output Error and Their Effective VLSI Implementation(Digital Signal Processing, Papers Selected from the 19th Symposium on Signal Processing)
- Novel Register Sharing in Datapath for Structural Robustness against Delay Variation
- Simultaneous Optimization of Skew and Control Step Assignments in RT-Datapath Synthesis
- Optimal Register Assignment with Minimum-Path Delay Compensation for Variation-Aware Datapaths
- DSP Code Optimization Utilizing Memory Addressing Operation (Special Section on Digital Signal Processing)
- The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006
- A Hidden Semi-Markov Model-Based Speech Synthesis System(Speech and Hearing)
- State Duration Modeling for HMM-Based Speech Synthesis(Speech and Hearing)
- A Training Method of Average Voice Model for HMM-Based Speech Synthesis(Digital Signal Processing)
- A Context Clustering Technique for Average Voice Models (Special Issue on Speech Information Processing)
- Speaker Adaptation of Pitch and Spectrum for HMM-Based Speech Synthesis
- Multi-Space Probability Distribution HMM(Special Issue on the 2000 IEICE Excellent Paper Award)
- Vector Quantization of Speech Spectral Parameters Using Statistics of Static and Dynamic Features
- Text-Independent Speaker Identification Using Gaussian Mixture Models Based on Multi-Space Probability Distribution (Special Issue on Biometric Person Authentication)
- A Test Generation Framework using Checker Circuits and its Application to Path Delay Test Generation
- A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation
- A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System
- Mixture Density Models Based on Mel-Cepstral Representation of Gaussian Process(Digital Signal Processing)
- A 16kb/s Wideband CELP-Based Speech Coder Using Mel-Generalized Cepstral Analysis
- Minimization of Output Errors of FIR Digital Filters by Multiple Decompositions of Signal Word
- Analysis and Minimization of Output Errors of 2-D Non-separable FIR Digital Filters with Finite Precision Internal Signals (Special Section on Digital Signal Processing)
- LMS-Based Algorithms with Multi-Band Decomposition of the Estimation Error Applied to System Identification (Special Section on Digital Signal Processing)
- Modular Array Structures for Design and Multiplierless Realization of Two-Dimensional Linear Phase FIR Digital Filters
- Multi-Band Decomposition of the Linear Prediction Error Applied to Adaptive AR Spectral Estimation
- Fast FIR Digital Filter Structures Using Minimal Number of Adders and Its Application to Filter Design (Special Section on Digital Signal Processing)
- Multiplierless Arrays for Realization of Lowpass and Highpass Linear Phase FIR Digital Filters (Special Section on Digital Signal Processing)
- Design of Non-Separable 3-D QMF Banks Using McClellan Transformations
- Design of FIR Digital Filters Using Estimates of Error Function over CSD Coefficient Space (Special Section of Selected Papers from the 8th Karuizawa Workshop on Circuits and Systems)
- DSP Compiler for Matrix and Vector Expressions with Automatic Computational Ordering
- 2-D Variable FIR Filters Using 3-D Prototype Filters
- Graceful Degradation for Multiprocessor Realization of Maximally Flat FIR Digital Filters (Special Issue on Super Chip for Intelligent Integrated Systems)
- Parallel and Modular Structures for FIR Digital Filters (Special Section on the 6th Karuizawa Workshop on Circuits and Systems)
- A Synthesis of Variable Wave Digital Filters
- Interval Properties of Lattice Allpass Filters with Applications
- A Design Method for 3Dimensional Band-Limiting FIR Filters Using McClellan Transformation (Special Section of Papers Selected from the 7th Digital Signal Processing Symymposium
- A Synthesis of Complex Allpass Circuits Using the Factorization of Scattering Matrices : Explicit Formulae for Even-Order Real Complementary Filters Having Butterworth or Chebyshev Responses (Special Section on the 5th Karuizawa Workshop on Circuits and S
- Design of Checkerboard-Distortion-Free Multidimensional Multirate Filters(Special Section on Digital Signal Processing)
- Checking Scheme for ABFT Systems Based on Modified PD Graph under an Error Generation/Propagation Model (Special Section of Papers Selected from ITC-CSCC '98)
- Adaptive AR Spectral Estimation Based on Wavelet Decomposition of the Linear Prediction Error
- Fast and Accurate Generalized Harmonic Analysis and Its Parallel Computation by GPU
- A Covariance-Typing Technique for HMM-Based Speech Synthesis
- An integer programming formulation for generating high quality transition tests (システムLSI設計技術・デザインガイア2008--VLSI設計の新しい大地)
- Assignment-Driven Loop Pipeline Scheduling and Its Application to Data-Path Synthesis
- An integer programming formulation for generating high quality transition tests (ディペンダブルコンピューティング・デザインガイア2008--VLSI設計の新しい大地)
- An integer programming formulation for generating high quality transition tests (VLSI設計技術・デザインガイア2008--VLSI設計の新しい大地)
- A Systematic Design of Fault Tolerant Systolic Arrays Based on Triple Modular Redundancy in Time-Processor Space
- Statistical Analysis Driven Synthesis of Application Specific Asynchronous Systems
- A-3-5 A Heuristic Approach to Detecting Transition Faults at All Circuit Outputs
- Characterization and Computation of Steiner Routing Based on Elmore's Delay Model
- Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Eigensignals of Downsamplers in Time and Transform Domains(Digital Signal Processing)
- Discrete Wirtinger-Type Inequalities for Gauging the Power of Sinusoids Buried in Noise
- Explicit Formula for Predictive FIR Filters and Differentiators Using Hahn Orthogonal Polynomials(Papers Selected from the 21st Symposium on Signal Processing)
- Stereophonic Acoustic Echo Canceler Based on Two-Filter Scheme(Papers Selected from the 21st Symposium on Signal Processing)
- Synthesis of 2-Channel IIR Paraunitary Filter Banks by Successive Extraction of 2-Port Lattice Sections
- Memory Allocation Method for Indirect Addressing DSPs with ±2 Update Operations
- Stable Single-Bit Noise-Shaping Quantizer Based on Σ△ Modulation and Successive Data Coding into Pre-Optimized Binary Vectors(Special Section on Digital Signal Processing)
- Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Continuous Speech Recognition Based on General Factor Dependent Acoustic Models(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
- Multiple-Image-Based Restoration for Motion Blur with Non-uniform Point Spread Function
- Restoration of Images Degraded by Linear Motion Blurred Objects in Still Background
- Identification of Piecewise Linear Uniform Motion Blur
- Bandwidth Extension with Hybrid Signal Extrapolation for Audio Coding(Papers Selected from the 21st Symposium on Signal Processing)
- A Change Detection Method for Image Sequences Based on Physical Models(Image, Papers Selected from the 19th Symposium on Signal Processing)
- Bayesian Context Clustering Using Cross Validation for Speech Recognition
- Dithered Subband Coding with Spectral Subtraction(Digital Signal Processing)
- DSP Code Optimization Methods Utilizing Addressing Operations at the Codes without Memory Accesses
- Performance Enhancement on Digital Signal Processors with Complex Arithmetic Capability (Special Section on VLSI for Digital Signal Processing)
- Speech recognition based on statistical models including multiple phonetic decision trees
- Analytic Constructions of Periodic and Non-periodic Complementary Sequences(Digital Signal Processing)
- A-4-1 DCT-Domain Blind Watermarking Technique with High Robustness against JPEG Compression
- Filter Bank Implementation of the Shift Operation in Orthonormal Wavelet Bases (Special Section of Selected Papers from the 8th Karuizawa Workshop on Circuits and Systems)
- Backward-Data-Direction Clocking and Relevant Optimal Register Assignment in Datapath Synthesis
- Design of High-Order Noise-Shaping FIR Filters for Overload-Free Stable Single- and Multi-Bit Data Converters(Digital Signal Processing)
- Wavelet Bases Obtained from the Raised-Cosine Filter
- Flexible Test Scheduling for an Asynchronous On-Chip Interconnect through Special Data Transfer
- A Formal Approach to Optimal Register Binding with Ordered Clocking for Clock-Skew Tolerant Datapaths
- A Bayesian Framework Using Multiple Model Structures for Speech Recognition
- An Extension of Separable Lattice 2-D HMMs for Rotational Data Variations
- Passive Two-dimensional Wave Digital Filters used in a Multirate System having Perfect Reconstruction
- Speaker interpolation for HMM-based speech synthesis system
- Dual-Edge-Triggered Flip-Flop-Based High-Level Synthesis with Programmable Duty Cycle
- Framework for Latch-based High-level Synthesis Using Minimum-delay Compensation
- A Bayesian Framework Using Multiple Model Structures for Speech Recognition