Bachelors project summary
- 1. PRINCIPLES OF SPEECH RECOGNITION Speech recognition can be classified into identification and verification. Speech identification is the process of determining which registered speaker provides a given utterance. Speech verification, on the other hand, is the process of accepting or rejecting the identity claim of a speaker. Figure 1 shows the basic structures of speech identification and verification systems. All technologies of speech recognition, identification and verification, each have its own advantages and disadvantages and might require different treatment and techniques. The choice of which technology to use is application-specific. At the highest level, all speech recognition systems contain two main modules (refer to Figure 1): feature extraction and feature matching. Feature extraction is the process that extracts a small amount of data from the voice signal that can later be used to represent each string. Feature matching involves the actual procedure to identify the unknown string by comparing extracted features from his/her voice input with the ones from a set of known speakers. We will discuss each module in detail in later sections. (a) Speaker identification Input speech Feature extraction Reference model (Speaker #1) Similarity Reference model (Speaker #N) Similarity Maximum selection Identification result (Speaker ID)
- 2. (b) Speaker verification Figure 1.1 Basic structures of speaker recognition system All speaker recognition systems have to serve two distinguished phases. The first one is referred to the enrolment or training phase, while the second one is referred to as the operational or testing phase. In the training phase, each registered speaker has to provide samples of their speech so that the system can build or train a reference model for that speaker. In case of speaker verification systems, in addition, a speaker-specific threshold is also computed from the training samples. In the testing phase, the input speech is matched with stored reference model(s) and a recognition decision is made. Speech signals in training and testing sessions can be greatly different due to many facts such as people voice change with time, health conditions (e.g. the speaker has a cold), speaking rates, and so on. There are also other factors, beyond speaker variability, that present a challenge to speaker recognition technology. Examples of these are acoustical noise and variations in recording environments (e.g. speaker uses different telephone handsets). Reference model (Speaker #M) Similarity Input speech Feature extraction Verification result (Accept/Reject) Decision ThresholdSpeaker ID (#M)
- 3. SPEECH ANALYSIS OVERVIEW Phonetics is part of the linguistic sciences. It is concerned with the sounds produced by the human vocal organs, and more specifically, the sounds which are used in human speech. One important aspect of Phonetics research is the instrumental analysis of speech. This is often referred to as experimental Phonetics or machines Phonetics. The Speech Analysis Series is a series of articles examining different aspects of presentation analysis. One will learn how to study a speech and how to deliver an effective speech evaluation. Later articles will examine Toastmasters evaluation contests and speech evaluation forms and resources. The document describes how to build a simple, yet complete and representative speech recognition system. Such a speech recognition system has potential in many security applications. For example, users have to speak a PIN (Personal Identification Number) in order to gain access to the laboratory door, or users have to speak their credit card number over the telephone line to verify their identity. By checking the voice characteristics of the input utterance, using an speech recognition system similar to the one that we will describe, the system is able to add an extra level of security NOTE: The sounds in this demo are down sampled to 8 bit, 8000Hz. You may want to widen you browser’s window to view the images.
- 4. FEATURE EXTRACTION OVERVIEW The purpose of this module is to convert the speech waveform of some type of parametric representation (at a considerably lower information rate) for further analysis and processing. This is often referred as the signal-processing front end. The speech signal is a slowly timed varying signal (it is called quasi-stationary). An example of speech signal is shown in Figure 2. When examined over a sufficiently short period of time (between 5 and 100 msec), its characteristics are fairly stationary. However, over long periods of time (on the order of 1/5 seconds or more) the signal characteristic change to reflect the different speech sounds being spoken. Therefore, short-time spectral analysis is the most common way to characterize the speech signal.
- 5. FEATURE MATCHING OVERVIEW The problem of speech recognition belongs to a much broader topic in scientific and engineering so called pattern recognition. The goal of pattern recognition is to classify objects of interest into one of a number of categories or classes. The objects of interest are generically called patterns and in our case are sequences of acoustic vectors that are extracted from an input speech using the techniques described in the previous section. The classes here refer to individual speakers. Since the classification procedure in our case is applied on extracted features, it can be also referred to as feature matching. Furthermore, if there exists some set of patterns that the individual classes of which are already known, then one has a problem in supervised pattern recognition. These patterns comprise the training set and are used to derive a classification algorithm. The remaining patterns are then used to test the classification algorithm; these patterns are collectively referred to as the test set. If the correct classes of the individual patterns in the test set are also known, then one can evaluate the performance of the algorithm. The state-of-the-art in feature matching techniques used in speaker recognition include Dynamic Time Warping (DTW), Hidden Markov Modeling (HMM), and Vector Quantization (VQ). In this project, the VQ approach will be used, due to ease of implementation and high accuracy. VQ is a process of mapping vectors from a large vector space to a finite number of regions in that space. Each region is called a cluster and can be represented by its center called a codeword. The collection of all codewords is called a codebook. Figure 4.1 shows a conceptual diagram to illustrate this recognition process. In the figure, only two speakers and two dimensions of the acoustic space are shown. The circles refer to the acoustic vectors from the speaker 1 while the triangles are from the speaker 2. In the training phase, using the clustering algorithm described in Section 4.2, a speaker-specific VQ codebook is generated for each known speaker by clustering his/her training acoustic vectors. The result codewords (centroids) are shown in Figure 5 by black circles and black triangles for speaker 1 and 2, respectively. The distance from a vector to the closest codeword of a codebook is called a VQ-distortion. In the recognition phase, an input utterance of an unknown voice is “vector-quantized” using each trained codebook and the total VQ distortion is computed. The speaker corresponding to the VQ codebook with smallest total distortion is identified as the speaker of the input utterance.