Person authentication systems that use a single biometric trait often have to contend with noisy sensor data, restricted degrees of freedom and unacceptable error rates. Attempting to improve the performance of individual matcher in such situations may not prove to be effective because of these inherent problems. A robust identification system may require fusion of several modalities because ambiguities in one modality may be compensated by another modality. This book addresses the problem of biometric fusion in verification systems. It begins with an introduction to face, speech and fingerprint, three most popular biometric traits, followed by the discussion of multimodal biometric systems. Besides the introduction to the multimodal theory, this book also provides complete source codes for a reader to execute a multimodal biometric authentication task. It will be a good starting point for readers to understand the contents in this book or develop their own systems. The author hopes that this book will serve as a reference to students, researchers and industrial practitioners in the field of multimodal biometric authentication and face, speech or fingerprint-related applications.