Figure 3 - uploaded by Ziad A.A Al Qadi
Content may be subject to copyright.
Source publication
Digital voice signal is one of the most widely used type of digital data, it is an important and applicable type of data, & it is used in various applications such human identification systems. Digital voice file usually has a big Size, which means increasing the complexity of the recognition system and decreasing the identification system efficien...
Citations
... One of the most papular features extraction methods is LBP based method [21], [22], [23], [24], the features will be extracted based on LBP operator and as shown in table 3, by this modified LBP method we can generate a 4 elements features array [11[, [15], [16]for each speech file. ...
... One of the most papular features extraction methods is LBP based method [21], [22], [23], [24], the features will be extracted based on LBP operator and as shown in table 3, by this modified LBP method we can generate a 4 elements features array [11[, [15], [16]for each speech file. ...
Human speech digital signals are famous and important digital types, they are used in many vital applications which require a high speed processing, so creating a speech signal features is a needed issue. In this research paper we will study more widely used methods of features extraction, we will implement them, and the obtained experimental results will be compared, efficiency parameters such as extraction time and throughput will be obtained and a speedup of each method will be calculated. Speech signal histogram will be used to improve some methods efficiency.
... Creating speech identifier is an important task in building any speech recognition system, many methods were introduced to create a speech signal features, some of these methods were based on calculating local binary pattern (LBP) [13], [14], some of them were based on calculating the coeffecient of linear prediction coding(LPC) [15], [16], [17], [18], some of them were based on using kmeans method of clustering [19], [20], [21], [22] . These methods are effeciently used in creating speech signal features, but here in our research paper we will show how WPT is efficient and how it provides a user of varieties in selecting the speech signal features [31], [32]. ...
Human speech signal is widely used in various vital applications such as computer security system, speech signal usually has big size, which make it difficult to identify the speech by direct matching, sample by sample, so the process of using an efficient and accurate method of creating speech print is an important task in speech identification process. In this research paper we will introduce a wavelet packet decomposition, the generated wavelet packet tree will be analyzed in order to create a unique features (identifier) to each speech signal, we will show how wavelet packet decomposition is flexible in creating speeches identifiers by providing a variety of selections, each features selection will lead to generate a unique and small in size identifier, which can be used later on in any application requiring human speech recognition.
