The future commercialization of speaker- and speech-recognition technology is impeded by the large degradation in system performance due to environmental differences between training and testing conditions. This is known as the "mismatched condition." Studies have shown [l] that most contemporary systems achieve good recognition performance if the conditions during training are similar to those during operation (matched conditions). Frequently, mismatched conditions axe present in which the performance is dramatically degraded as compared to the ideal matched conditions. A common example of this mismatch is when training is done on clean speech and testing is performed on noise- or channel-corrupted speech. Robust speech techniques [2] attempt to maintain the performance of a speech processing system under such diverse conditions of operation. This article presents an overview of current speaker-recognition systems and the problems encountered in operation, and it focuses on the front-end feature extraction process of robust speech techniques as a method of improvement. Linear predictive (LP) analysis, the first step of feature extraction, is discussed, and various robust cepstral features derived from LP coefficients are described. Also described is the afJine transform, which is a feature transformation approach that integrates mismatch to simultaneously combat both channel and noise distortion.

Robust speaker recognition: a feature-based approach

An evaluation of various classifiers for text-independent speaker recognition is presented. In addition, a new classifier is examined for this application. The new classifier is called the modified neural tree network (MNTN). The MNTN is a hierarchical classifier that combines the properties of decision trees and feedforward neural networks. The MNTN differs from the standard NTN in both the new learning rule used and the pruning criteria. The MNTN is evaluated for several speaker recognition experiments. These include closed- and open-set speaker identification and speaker verification. The database used is a subset of the TIMIT database consisting of 38 speakers from the same dialect region. The MNTN is compared with nearest neighbor classifiers, full-search, and tree-structured vector quantization (VQ) classifiers, multilayer perceptrons (MLPs), and decision trees. For closed-set speaker identification experiments, the full-search VQ classifier and MNTN demonstrate comparable performance. Both methods perform significantly better than the other classifiers for this task. The MNTN and full-search VQ classifiers are also compared for several speaker verification and open-set speaker-identification experiments. The MNTN is found to perform better than full-search VQ classifiers for both of these applications. In addition to matching or exceeding the performance of the VQ classifier for these applications, the MNTN also provides a logarithmic saving for retrieval. >

Speaker recognition using neural networks and conventional classifiers

Front-end or feature extractor is the first component in an automatic speaker recognition system. Feature extraction transforms the raw speech signal into a compact but effective representation that is more stable and discriminative than the original signal. Since the front-end is the first component in the chain, the quality of the later components (speaker modeling and pattern matching) is strongly determined by the quality of the front-end. In other words, classification can be at most as accurate as the features. Several feature extraction methods have been proposed, and successfully exploited in the speaker recognition task. However, almost exclusively, the methods are adopted directly from the speech recognition task. This is somewhat ironical, considering the opposite nature of the two tasks. In speech recognition, speaker variability is one of the major error sources, whereas in speaker recognition it is the information that we wish to extract. The mel-frequency cepstral coefficients (MFCC) is the most evident example of a feature set that is extensively used in speaker recognition, but originally developed for speech recognition purposes. When MFCC front-end is used in speaker recognition system, one makes an implicit assumption that the human hearing meachanism is the optimal speaker recognizer. However, this has not been confirmed, and in fact opposite results exist. Although several methods adopted from speech recognition have shown to work well in practise, they are often used as “black boxes” with fixed parameters. It is not understood what kind of information the features capture from the speech signal. Understanding the features at some level requires experience from specific areas such as speech physiology, acoustic phonetics, digital signal processing and statistical pattern recognition. According to the author’s general impression of literature, it seems more and more that currently, at the best we are guessing what is the code in the signal that carries our individuality. This thesis has two main purposes. On the one hand, we attempt to see the feature extraction as a whole, starting from understanding the speech production process, what is known about speaker individuality, and then going

http://cs.joensuu.fi/pages/pums/public_results/2004_PhLic_Kinnunen_Tomi.pdf

Spectral Features for Automatic Text-Independent Speaker Recognition

Background environmental noises degrade the performance of speech-processing systems (e.g. speech coding, speech recognition). By modifying the processing according to the type of background noise, the performance can be enhanced. This requires noise classification. In this paper, four pattern-recognition frameworks have been used to design noise classification algorithms. Classification is done on a frame-by-frame basis (e.g. once every 20 ms). Five commonly encountered noises in mobile telephony (i.e. car, street, babble, factory, and bus) have been considered in our study. Our experimental results show that the line spectral frequencies (LSFs) are robust features in distinguishing the different classes of noises.

/pdf/frame-level-noise-classification-in-mobile-environments-22p7o2acn5.pdf

Frame level noise classification in mobile environments

Properties of line spectrum pair polynomials: a review

Four varieties of line spectrum pair (LSP) frequencies for speaker recognition applications and their corresponding performances are studied. The four varieties are all-LSP frequencies, odd or even line spectrum frequencies, the mean of adjacent LSP frequencies, and the difference of adjacent LSP frequencies. A speaker-based vector quantization approach is used in the evaluation. The results show that each variety of LSP frequencies has a very high accurate rate. >

C.-S. Liu

Papers

Study of line spectrum pair frequencies for speaker recognition