Voice recognition by computer

Voice recognition, often called speaker recognition, is the complement of speech recognition. In speech recognition, the computer tries to extract linguistic information from the speech signal to the exclusion of personal information. Conversely, voice recognition requires the computer to focus on the characteristics unique to the individual, disregarding the actual word spoken. The ability to identify people uniquely by their voices alone leads to several application areas. Law enforcement and military security authorities were among the first to make use of speaker recognition technology. To date, the increase in application opportunities has resulted in increased interest in speaker recognition research. The purpose of this work is to provide an interpretative overview and perspective of computer voice recognition systems and evaluation methodology. It is in this context that we present our own results in some special areas of voice recognition, e. g. disclosure of professional imitator, analysis of speech under stress, and effect of alcohol on speech. Because this book is an adapted scholarly work, it is suitable for professionals in both industrial and academic milieus who wish to pursue voice recognition beyond the leading edge.