检索结果-内蒙古大学图书馆

DWT and LPC based feature extraction methods for isolated word recognition

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2012年第1期2012卷 1-7页

作者： Nehe, Navnath S. Holambe, Raghunath S. Pravara Rural Engn Coll Dept Instrumentat Engn Loni 413736 Maharashtra India SGGS Inst Engn & Technol Nanded Maharashtra India

In this article, new feature extraction methods, which utilize wavelet decomposition and reduced order linear predictive coding (LPC) coefficients, have been proposed for speech recognition. The coefficients have been derived from the speech frames decomposed using discrete wavelet transform. LPC coefficients derived from subband decomposition (abbreviated as WLPC) of speech frame provide better representation than modeling the frame directly. The WLPC coefficients have been further normalized in cepstrum domain to get new set of features denoted as wavelet subband cepstral mean normalized features. The proposed approaches provide effective (better recognition rate), efficient (reduced feature vector dimension), and noise robust features. The performance of these techniques have been evaluated on the TI-46 isolated word database and own created Marathi digits database in a white noise environment using the continuous density hidden Markov model. The experimental results also show the superiority of the proposed techniques over the conventional methods like linear predictive cepstral coefficients, Mel-frequency cepstral coefficients, spectral subtraction, and cepstral mean normalization in presence of additive white Gaussian noise.

关键词： feature extraction linear predictive coding discrete wavelet transform cepstral mean normalization hidden Markov model

来源：评论

学校读者我要写书评

暂无评论

SPEECH coding - A TUTORIAL REVIEW

引用

PROCEEDINGS OF THE IEEE 1994年第10期82卷 1541-1582页

作者： SPANIAS, AS Dept. of Electr. Eng. Arizona State Univ. Tempe AZ

The past decade has witnessed substantial progress towards the application of low-rate speech coders to civilian and military communications as well as computer-related voice applications. Central to this progress has been the development of new speech coders capable of producing high-quality speech at low data rates. Most of these coders incorporate mechanisms to: represent the spectral properties of speech, provide for speech waveform matching, and ''optimize'' the coder's performance for the human ear. A number of these coders have already been adopted in national and international cellular telephony standards. The objective of this paper is to provide a tutorial overview of speech coding methodologies with emphasis on those algorithms that are part of the recent low-rate standards for cellular communications. Although the emphasis is on the new low-rate coders, we attempt to provide a comprehensive survey by covering some of the traditional methodologies as well. We feel that this approach will not only point out key references but will also provide valuable background to the beginner. The paper starts with a historical perspective and continues with a brief discussion on the speech properties and performance measures. We then proceed with descriptions of waveform coders, sinusoidal transform coders, linear predictive vocoders, and analysis-by-synthesis linear predictive coders. Finally, we present concluding remarks followed by a discussion of opportunities for future research.

关键词： analysis-by-synthesis linear predictive coders cellular communications cellular radio high-quality speech linear predictive coding linear predictive vocoders low-rate speech coders performance measures radiotelephony sinusoidal transform coders speech coding speech properties speech waveform matching vocoders waveform coders

来源：评论

学校读者我要写书评

暂无评论

SE(3) Based LTV-MPC Algorithm for Multi-Obstacle Trajectory Tracking of Fully Driven Spacecraft

引用

IEEE ACCESS 2024年 12卷 37850-37861页

作者： Wang, Wenbang Peng, Xiaokang Ai, Jia Fu, Cheng Li, Chaobo Zhang, Zejian Hubei Univ Technol Sch Mech Engn Wuhan 430068 Peoples R China Shanghai Inst Mech & Elect Engn Shanghai 200000 Peoples R China Wuhan Railway Vocat Coll Technol Wuhan 430074 Peoples R China Hubei Inst Logist Technol Xiangyang 441000 Hubei Peoples R China

A linear time-varying model predictive control (LTV-MPC) method based on SE(3) is proposed, to enhance the control precision and reduce energy consumption of the spacecraft. First, left-invariant principle of Lie group, Lie algebra SO(3) , and other differential geometry theories are applied to extend LTV-MPC to SE(3) . Then, considering the obstacle avoidance problem of the spacecraft in space, a suitable optimization function is selected to ensure smooth tracking of the desired working trajectory. By controlling the incremental output with the fastest convergence rate, the controller enables effective trajectory tracking. Finally, the effectiveness and applicability of the controller are verified by simulation experiments. These simulations validate the controller's ability to achieve constraint satisfaction, optimize transient processes, and enhance control accuracy. The results provide compelling evidence of the controller's potential for real-world spacecraft control applications.

关键词： Space vehicles Attitude control Orbits Mathematical models Force Collision avoidance Trajectory tracking Time-varying systems predictive control linear predictive coding LTV-MPC SE(3) spacecraft obstacle avoidance trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

SOME PRELIMINARY EXPERIMENTS IN RECOGNITION OF CONNECTED DIGITS

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING 1976年第2期24卷 170-182页

作者： RABINER, LR SAMBUR, MR BELL TEL LABS INC MURRAY HILL NJ 07974 USA

This paper describes an implementation of a speaker independent system which can recognize connected digits. The overall recognition system consists of two separate but interrelated parts. The function of the first part of the system is to segment the digit string into the individual digits which comprise the string; the second part of the system then recognizes the individual digits based on the results of the segmentation. The segmentation of the digits is based on a voiced-unvoiced analysis of the digit string, as well as information about the location and amplitude of minima in the energy contour of the utterance. The digit recognition strategy is similar to the algorithm used by Sambur and Rabiner [1] for isolated digits, but with several important modifications due to the impreciseness with which the exact digit boundaries can be located. To evaluate the accuracy of the system in segmenting and recognizing digit strings a series of experiments was conducted. Using high-quality recordings from a soundproof booth the segmentation accuracy was found to be about 99 percent, and the recognition accuracy was about 91 percent across ten speakers (five male, five female). With recordings made in a noisy computer room the segmentation accuracy remained close to 99 percent, and the recognition accuracy was about 87 percent across another group of ten speakers (five male, five female).

关键词： Speech recognition Speech analysis linear predictive coding Energy measurement Telephony Application software Area measurement Autocorrelation Information analysis Acoustical engineering

来源：评论

学校读者我要写书评

暂无评论

DESIGN OF IIR/FIR FILTERS USING A FREQUENCY-DOMAIN BOOTSTRAPPING TECHNIQUE AND LPC METHODS

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING 1983年第4期31卷 999-1006页

作者： SCHMID, CE Marine Systems Division Honeywell Inc. Seattle WA USA

A technique is described for designing IIR/FIR digital filters which are specified by the number of poles and zeros, the sampling frequency, and a magnitude response versus frequency. The iterative technique to carry out the design bootstraps back and forth between the IIR (all pole) section and FIR (all zero) section, updating the design each time in the frequency domain using the data from the previous IIR or FIR section and the desired filter response. Coefficient calculations at each iteration are based upon standard LPC (linear prediction coefficient) and inverse LPC methods. An efficient computer program has been written to implement the technique using Levinson and FFT pruning algorithms. The combination of the efficiency from LPC and pruning methods, and the ease of iteration and interpretation in the frequency domain creates a straightforward and workable computer program for general digital filter design based upon spectral magnitude specifications. Examples of the filter design program illustrate how well the technique works as a function of the number of iterations.

关键词： Finite impulse response filter Frequency domain analysis linear predictive coding IIR filters Poles and zeros Signal design Fourier transforms Speech analysis Sampling methods Digital filters

来源：评论

学校读者我要写书评

暂无评论

On improving performance of analysis by synthesis speech coders

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING 1996年第3期4卷 243-247页

作者： Cucchi, S Fratti, M Ronchi, M Alcatel Telettra Inc. Milan Italy

An algorithm for improving the performance of analysis-by-synthesis (A-by-S) speech coders is presented. It is shown that proper modifications of the A-by-S strategies commonly used to determine the excitation parameters can be devised. In particular, a redefinition of the classical objective function based on the weighted mean squared error criterion may allow a better tracking of the speech signal transients as well as a better alignement of the synthetic pitch pulses. The implementation details of the algorithm are discussed and experimental results are presented.

关键词： Speech analysis Speech synthesis Performance analysis linear predictive coding Bit rate Filters Algorithm design and analysis Signal synthesis Convergence Degradation

来源：评论

学校读者我要写书评

暂无评论

Two-stage optimisation algorithm for adaptive IIR notch filter

引用

ELECTRONICS LETTERS 2014年第14期50卷 985-U96页

作者： Peng, Renhua Zheng, Chengshi Li, Xiaodong Chinese Acad Sci Commun Acoust Lab Inst Acoust Beijing 100190 Peoples R China Chinese Acad Sci Shanghai Adv Res Inst Acoust & Informat Technol Lab Beijing 100190 Peoples R China

The performances of the linear prediction (LP) algorithm and the indirect plain gradient (IPG) algorithm for the adaptive infinite-impulse-response (IIR) notch filter are theoretically studied, and the two phenomena in these two algorithms are revealed. First, the LP algorithm has a faster convergence speed than the IPG algorithm when the initial adjusted value is far away from the optimal solution. Secondly, the IPG algorithm has a much smaller estimation bias and mean squared error than the LP algorithm in a steady state. On the basis of these facts, a two-stage optimisation algorithm is proposed to make full use of the advantages of both the LP algorithm and the IPG algorithm. Simulation results show that the proposed algorithm can improve the convergence rate while keeping the same steady state as the IPG algorithm.

关键词： IMPULSE response MATHEMATICAL optimization STOCHASTIC convergence ALGORITHMS linear predictive coding

来源：评论

学校读者我要写书评

暂无评论

Digital filter interpolation of decoded LSFs for distributed continuous speech recognition

引用

ELECTRONICS LETTERS 2008年第17期44卷 1039-U50页

作者： de Alencar, V. F. S. Alcaim, A. Catholic Univ CETUC PUC RIO Ctr Telecommun Studies BR-22453 Rio De Janeiro Brazil

A digital filter interpolation of decoded line spectral frequencies (LSFs) that significantly outperforms linear interpolation for large vocabulary distributed continuous speech recognition systems is presented. Experiments were conducted using linear predictive coding (LPC) and LSF-derived speech recognition features, CDHMM acoustic models, triphone units and trigram language models for Brazilian Portuguese.

关键词： decoding digital filters linear predictive coding speech recognition acoustic models decoded line spectral frequencies digital filter interpolation linear interpolation speech recognition features trigram language models triphone DEcoding modelling languages Continuous speech recognition linearly independant Digital filters Acoustic models three-component geophone

来源：评论

学校读者我要写书评

暂无评论

HUMAN SPEAKER RECOGNITION PERFORMANCE OF LPC VOICE PROCESSORS

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING 1985年第3期33卷 752-753页

作者： UZDY, Z AeroSpace Corporation El Segundo CA USA

Immediate identification of speakers' voices can be highly important to efficient communication in certain applications. This correspondence describes an experimental investigation to determine the human speaker recognition performance of LPC voice processors. A small group of coworkers were used as the test subjects. The test results indicate the importance of high-frequency data bandwidth for speaker recognition.

关键词： Humans Speaker recognition linear predictive coding Aerospace testing Speech processing Telephone sets Telephony Materials testing Bandwidth Speech coding

来源：评论

学校读者我要写书评

暂无评论

Low-delay subband CELP coding for wideband speech

引用

IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING 1997年第5期144卷 313-316页

作者： Tian, WS Wong, WC Tsao, C Natl Univ Singapore Dept Elect Engn Singapore 119260 Singapore

Low-delay techniques are proposed for coding 7 kHz speech using subband code-excited linear predictive coding (CELP). The use of separate and joint index codebooks is compared. Specifically, the joint-index-subband CELP (JISBC) algorithm is found to provide good quality with processing delay in the range 2.375-3.375 ms at corresponding bit rates of 16-8 k bit/s.

关键词： coding linear predictive coding speech transmission

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：