An 800 bps speech compression system based on vector quantization

1980 ◽  
Vol 68 (S1) ◽  
pp. S88-S88 ◽  
Author(s):  
David Y. Wong ◽  
Fred B. Juang ◽  
A. H. Gray
Keyword(s):  
Vector Quantization ◽  
Speech Compression ◽  
Compression System

Adaptive Speech Compression Based on Discrete Wave Atoms Transform

2016 ◽  
Vol 6 (5) ◽  
pp. 2150
Author(s):  
Bousselmi Souha ◽  
Aloui Nouredine ◽  
Cherif Adnane
Keyword(s):  
Compression Ratio ◽  
Speech Quality ◽  
Huffman Coding ◽  
Current Work ◽  
Speech Compression ◽  
Snr Estimation ◽  
Run Length ◽  
Compression System ◽  
Wave Atoms ◽  
Wavelets Transform

<p>This paper proposes a new adaptive speech compression system based on discrete wave atoms transform. First, the signal is decomposed on wave atoms, then wave atom coefficients are truncated using a new adaptive thresholding which depends on the SNR estimation. The thresholded coefficients are quantized using Max Lloyd scalar quantizer. Besides, they are encoded using zero run length encoding followed by Huffman coding. Numerous simulations are performed to prove the robustness of our approach. The results of current work are compared with wavelet based compression by using objective criteria, namely CR, SNR, PSNR and NRMSE. This study shows that the wave atoms transform is more appropriate than wavelets transform since it offers a higher compression ratio and a better speech quality.</p>

scholarly journals Auditory Testing of a Formant‐Coding Speech Compression System

1956 ◽  
Vol 28 (4) ◽  
pp. 768-768
Author(s):  
James L. Flanagan ◽  
Arthur S. House
Keyword(s):  
Speech Compression ◽  
Compression System

An OLE-based speech compression system for multimedia applications

1998 ◽  
Vol 22 (1) ◽  
pp. 41-48
Author(s):  
T. Srikanthan ◽  
Goh Wee Leng ◽  
S.K. Amarasinghe
Keyword(s):  
Multimedia Applications ◽  
Speech Compression ◽  
Compression System

Vector Quantization for Speech Compression by a New Version of PRSOM

2018 ◽  
Vol 27 (03) ◽  
pp. 1850013 ◽  
Author(s):  
Fidae Harchli ◽  
Zakariae En-Naimani ◽  
Abdelatif Es-Safi ◽  
Mohamed Ettaouil
Keyword(s):  
Vector Quantization ◽  
Optimal Number ◽  
Self Organizing Map ◽  
Speech Compression ◽  
Stochastic Version ◽  
Probabilistic Network ◽  
Deviation Matrix ◽  
New Strategy

The self-organizing map (SOM) is a popular neural network which was designed for solving problems that involve tasks such as clustering and visualization. Especially, it provides a new strategy of clustering using a competition and co-operation principal. The probabilistic Kohonen network (PRSOM) is the stochastic version of classical one. However, determination of the optimal number of neurons, their initial weights vector and their deviation matrix is still a big problem in the literature. These parameters have a great impact on the learning process of the network, the convergence and the quality of results. Also determination of clusters’ number is a very difficult task. In this paper we propose a new method, called H-PRSOM, which looks for the optimal architecture of the map and determines the suitable codebook for speech compression. According to his hierarchical process, H-PRSOM identifies automatically, in each iteration, new initial parameters of the map. The generated parameters will be used in the learning phase of the probabilistic network. Due to its important propriety of initialization and optimization, we expect that the use of this new version of PRSOM algorithm in the vector quantization might provide good results. In order to evaluate its performance, H-PRSOM model is applied to the problem of speech compression of Arabic digits. The conducted experiments show that the proposed method is able to realize the expected goals.

Sign in / Sign up

Export Citation Format

Share Document