Pattern Recognition, 4th Edition

7.5. Typical Features for Speech and Audio Classification

As we have already commented in the Preface, speech recognition is a major application area of pattern recognition, and a number of speech-recognizing systems are already available in the market. Audio classification and recognition have also received a lot of attention in recent years. A great number of commercial applications are envisaged for the future in the field of multimedia databases. Techniques for automatic indexing tools, intelligent browsers, and search engines with content-based retrieval capabilities are currently the focus of a major research effort. In this context, audiovisual data segmentation and indexing, based not only on visual information but on the accompanying ...