Cross Correlation of Long-Term Speech Spectra as a Speaker Identification Technique
Acoustical analysis of the speech signal by means of long-term speech spectra recently has been established as a valid method of identifying speakers – at least in the laboratory. Moreover, a number of independent statistical techniques have been proposed for use as identification criteria when this method is utilized. The present report describes the development and testing of a cross-correlation statistical technique as a decision criterion and compares it with the Euclidean distance approach. Subjects were 100 male college students divided into two separate groups of 50 American and 50 Polish talkers. Speech material was a 2.5 min reading of a standard passage in the talkers' native language; test and reference samples were generated as a basis for the statistical evaluations. The cross-correlation techniques employed generally provided very high levels of speaker identification with at least one permitting almost errorless identification. Moreover, the present approach proved to be approximately equal to the Euclidean technique as a decision criterion. It is further suggested that the two methods used together could provide a more powerful basis for decisions when long-term speech spectra are utilized to identify individuals from their speech.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: November 1, 1975
More about this publication?
- Acta Acustica united with Acustica, published together with the European Acoustics Association (EAA), is an international, peer-reviewed journal on acoustics. It publishes original articles on all subjects in the field of acoustics, such as general linear acoustics, nonlinear acoustics, macrosonics, flow acoustics, atmospheric sound, underwater sound, ultrasonics, physical acoustics, structural acoustics, noise control, active control, environmental noise, building acoustics, room acoustics, acoustic materials, acoustic signal processing, computational and numerical acoustics, hearing, audiology and psychoacoustics, speech, musical acoustics, electroacoustics, auditory quality of systems. It reports on original scientific research in acoustics and on engineering applications. The journal considers scientific papers, technical and applied papers, book reviews, short communications, doctoral thesis abstracts, etc. In irregular intervals also special issues and review articles are published.
- Editorial Board
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Information for Advertisers
- Online User License
- Ingenta Connect is not responsible for the content or availability of external websites