检索结果-内蒙古大学图书馆

Gated recurrent unit predictor model-based adaptive differential pulse code modulation speech decoder

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2024年第1期2024卷 6页

作者： Sheferaw, Gebremichael Kibret Mwangi, Waweru Kimwele, Michael Mamuye, Adane Jomo Kenyatta Univ Agr & Technol Sch Comp & Informat Technol Nairobi Kenya Addis Ababa Univ Sch Informat Technol & Engn Inst Technol Addis Ababa Ethiopia

Speech coding is a method to reduce the amount of data needs to represent speech signals by exploiting the statistical properties of the speech signal. Recently, in the speech coding process, a neural network prediction model has gained attention as the reconstruction process of a nonlinear and nonstationary speech signal. This study proposes a novel approach to improve speech coding performance by using a gated recurrent unit (GRU)-based adaptive differential pulse code modulation (ADPCM) system. This GRU predictor model is trained using a data set of speech samples from the DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus actual sample and the ADPCM fixed-predictor output speech sample. Our contribution lies in the development of an algorithm for training the GRU predictive model that can improve its performance in speech coding prediction and a new offline trained predictive model for speech decoder. The results indicate that the proposed system significantly improves the accuracy of speech prediction, demonstrating its potential for speech prediction applications. Overall, this work presents a unique application of the GRU predictive model with ADPCM decoding in speech signal compression, providing a promising approach for future research in this field.

关键词： Speech coding Gated recurrent unit Nonlinear prediction Waveform coding Audio coding adaptive differential pulse code modulation Speech compression

来源：评论

学校读者我要写书评

暂无评论

adaptive PREDICTIVE IMAGE-CODING USING LOCAL CHARACTERISTICS

引用

IEE PROCEEDINGS-I COMMUNICATIONS SPEECH AND VISION 1989年第6期136卷 385-390页

作者： HSIEH, CH LU, PC LIOU, WG Department of Electrical Engineering Chung Cheng Institute of Technology Ta-Hsi Republic of China

The paper presents an efficient adaptive predictive coding method using the local characteristics of images. In this method, three coding schemes, namely, mean, subsampling combined with fixed DPCM, and ADPCM/PCM, are used and one of these is chosen adaptively based on the local characteristics of images. The prediction parameters of the 2-d linear predictor in the ADPCM/PCM are extracted on a block by block basis using the 2-d lattice filtering method. The order update 2-d lattice model proposed by Parker and Kayran is extended into order update and time update recursion for more efficient computation. Simulation results show that the proposed method is effective in reducing the slope overload distortion and the granular noise at low bit rates, and thus it can improve the visual quality of reconstructed images. Other advantages of this method are the low computational burden and the suitability for the VLSI implementation.

关键词： PCM adaptive differential pulse code modulation DPCM Pattern recognition VLSI implementation granular noise slope overload distortion codes picture processing filtering and prediction theory adaptive predictive image coding encoding pulse-code modulation local characteristics Optical information, image and video signal processing 2D linear predictor low bit rates prediction parameters visual quality reconstructed images differential pulse code modulation adaptive filters 2D lattice filtering time update recursion order update recursion ADPCM/PCM

来源：评论

学校读者我要写书评

暂无评论

EMBEDDED ADPCM WITH NOISE SPECTRAL SHAPING FOR PACKET VOICE TRANSMISSION

引用

ELECTRONICS LETTERS 1987年第5期23卷 239-241页

作者： KIM, HD UN, CK Communications Research Laboratory Department of Electrical Engineering Korea Advanced Institute of Science & Technology Seoul Korea

An embedded adaptive differential pulse code modulation (EADPCM) that may be used for speech coding in a packet network is proposed. In this scheme the quantisation nosie of an ADPCM is reduced significantly by employing an instant-aneously adaptive PCM (ADPCM) as a second-stage coder, and is shaped further to reduce the subjectively annoying effects by a noise-shaping filter. By computer simulation using real speech we show a significant performance improvement (3 to 10dB at rates of 16 to 48 kbit/s) with the proposed scheme.

关键词： EADPCM speech coding adaptive differential pulse code modulation noise spectral shaping modulation and coding methods 16 to 48 kbit/s computer simulation using real speech packet switching subjectively annoying effects instantaneously adaptive PCM voice communication noise-shaping filter pulse-code modulation quantisation noise APCM embedded ADPCM second-stage coder performance improvement packet network packet voice transmission Communication system theory digital simulation

来源：评论

学校读者我要写书评

暂无评论

ADPCM USING VECTOR PREDICTOR AND FORWARD adaptive QUANTIZER WITH STEP-SIZE PREDICTION

引用

ELECTRONICS LETTERS 1985年第2期21卷 74-75页

作者： WONG, KHJ STEELE, R Department of Electronics & Information Engineering University of Southampton Southampton UK

An adaptive differential pulse code modulation (ADPCM) system is described having a set of fixed vector predictors, and a quantiser that is adapted in the forward direction with the distinction that its step size is p... 详细信息

关键词： step-size prediction forward adaptive quantiser fixed vector predictors encoding pulse-code modulation codes adaptive differential pulse code modulation SNR gains analogue-digital conversion

来源：评论

学校读者我要写书评

暂无评论

Nonlinear backward ADPCM speech coding using kernel methods and online sparsification

引用

TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES 2014年第2期25卷 161-172页

作者： Alipoor, Ghasem Savoji, Mohammad Hassan Shahid Beheshti Univ Fac Elect & Comp Engn Tehran *** Iran

Modeling using neural networks and Volterra expansion are widely used in signal processing to account for nonlinear characteristics inherent in natural signals. In spite of their good performance in a wide range of applications, adaptive implementations of these models suffer from severe problems of a large number of parameters, slow convergence, and the risk of being trapped in local minima. Furthermore, inherent instability of the Volterra filters makes them unsuitable for applications that require synthesis or reconstruction, for example, speech coding. Nonetheless, kernel methods in the framework of reproducing kernel Hilbert spaces are emerging solutions that can tackle these problems by extending linear algorithms to spaces created by nonlinear mapping of the input signal. In this paper, we address the problems encountered in nonlinear adaptive coding by employing, for the first time, several kernel adaptive algorithms in the framework of speech coding using the adaptive differential pulse code modulation technique. Particular attention is focused on the effects of various sparsification techniques on the performance of the resultant algorithms. Simulation results show that utilizing kernel methods results in an average improvement of up to 3.4 dB in the signal-to-noise ratio of the reconstructed speech. This is while a lower improvement of up to 1.4 dB is achieved by exploiting Volterra filters at the cost of a demanding increase in the complexity, a slight increase in the bit-rate and introducing a relatively long delay. Copyright (c) 2012 John Wiley & Sons, Ltd.

关键词： kernel methods kernel adaptive filtering algorithms kernel least mean square algorithm kernel least-squares algorithms speech coding adaptive differential pulse code modulation

来源：评论

学校读者我要写书评

暂无评论

WIDEBAND SPEECH COMPRESSION USING CELP AND WAVELET TRANSFORM

WIDEBAND SPEECH COMPRESSION USING CELP AND WAVELET TRANSFORM

引用

1996 3rd International Conference on Signal Processing(ICSP’96)

作者： Yao Li Ru-wci Dai Jian-jian Feng Yong-gui Xie A1 Lab. Automation Inst.C.A.S. Radio-Electronics Dep. Beijing Normal University

ISBN: (纸本)0780329120

＜正＞The paper presents a new scheme for wideband speech coding in sub-bands, where the wideband speech signal is sampled at 16kH/ and 16 bits / sample,and the subband decomposition is performed using discrete orthogonal *** wavelet transform uses bandpass filters to split the speech signal into two frequency *** order to attain low bit rates,high quality speech and less computational complexity,each subband is then coded independently with improved CELP algorithms at low frequency-band and adaptive differential pulse code modulation （ADPCM ） coding at high frequency-band. The overall effect is to produce a wideband speech coder that has almost the same computational complexity as a narrowband CELP coding algorithms and the coding rate at 12.8kbit/s.

关键词： data compression speech coding wavelet transforms transform coding signal sampling linear predictive coding differential pulse code modulation computational complexity band-pass filters filtering theory wideband speech compression CELP wavelet transform speech coding signal sampling subband decomposition discrete orthogonal wavelets bandpass filters low bit rate high quality speech computational complexity adaptive differential pulse code modulation ADPCM subband coding 12.8 kbit/s

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：