Evaluation of Speech Enhancement Techniques for Speaker Identification in Noisy Environments

Multidimensional Features Extraction Methods in Frequency Domain

“…Next the estimated dynamical features vector is feed to a Gaussian Mixture Model, GMM, which is used to obtain a representative model for each speaker. Taking into account that a SRS can be improved taking the voiced part of the speech signal because this contains the main information relative to the speaker identity (El-Solh, 2007;Markov & Nakagawa, 1999;Plumper et al, 1999). For this reason in this book the features vector will be derived from the LPC-cepstral extracted only from the voiced part speech signal.…”

Multiengine Speech Processing Using SNR Estimator in Variable Noisy Environments

“…The results of [2] suggest that optimizing the quality of speech perception or SNR, using speech quality enhancement techniques, does not optimize speech processing performance. Indeed, speech quality enhancement techniques may actually degrade the speech processing performance instead of improving it.…”

“…The performance of most speech processing systems is degraded severely when the training and the testing audio are captured in different acoustic environments (e.g., different levels of noise [1][2][3][4]). For example, training speech may be captured using a telephone handset in a noise-free environment, while the test speech is captured using a handsfree phone in a noisy environment.…”

“…For example, training speech may be captured using a telephone handset in a noise-free environment, while the test speech is captured using a handsfree phone in a noisy environment. The conventional method to improve the performance of speech processing in noisy environments is to perform speech enhancement prior to speech processing [2][3][4][5][6][7]. In this method, training speech signals are obtained in a clean environment (i.e., no noise).…”

“…In [2], the effect of five different speech enhancement techniques on a GMM-based ASR system was examined. These enhancement techniques were (1) perceptual wavelet adaptive denoising (PWAD) (TPS-PWAD), (2) VAD-based noise floor estimation (VAD-NFE), (3) minimum-meansquare-error-based two-dimensional spectral enhancement (MMSE-TDSE), (4) two-pass adaptive noise estimation (TPANE), and (5) combined two-pass spectral and PWAD.…”