Verification effectiveness in open-set speaker identification
نویسندگان
چکیده
This paper is concerned with the verification effectiveness in open-set, text-independent speaker identification. The study includes an analysis of the characteristics of this mode of speaker recognition and the potential causes of errors. The use of well-known score normalisation techniques for the purpose enhancing the reliability of the process is described and their relative effectiveness is experimentally investigated. The experiments are based on the dataset proposed for the 1-speaker detection task of the NIST Speaker Recognition Evaluation 2003. Based on the experimental results, it is demonstrated that significant benefits is achieved by using score normalisation in open-set identification, and that the level of this depends highly on the type of the approach adopted. The results also show that better performance can be achieved by using the cohort normalisation methods. In particular, the unconstrained cohort method with a relatively small cohort size appears to outperform all other approaches.
منابع مشابه
Analysis of Top-k Strategies for Open-set Speaker Identification Applications
Recent performance gains in speaker verification systems suggest it is now viable to employ these systems in open-set speaker identification applications where an automated decision is passed to a human-in-the-loop for final analysis and decision. This paper examines the performance for when a speaker verification system expands into the identification domain. Our results indicate that separate...
متن کاملImproved Weighted Matching for Speaker Recognition
Matching algorithms have significant importance in speaker recognition. Feature vectors of the unknown utterance are compared to feature vectors of the modeled speakers as a last step in speaker recognition. A similarity score is found for every model in the speaker database. Depending on the type of speaker recognition, these scores are used to determine the author of unknown speech samples. F...
متن کاملImproving robustness in open set speaker identification by shallow source modeling
Open set speaker identification consists of deciding whether an input utterance corresponds to a target speaker or to an impostor. The most likely among a set of target speakers is hypothesized and verified. Speaker verification is performed by comparing the likelihood score of the most likely speaker model to the likelihood score of an impostor model, and then applying a suitable threshold. Th...
متن کاملAnalysis of multitarget detection for speaker and language recognition
The general multitarget detection (open-set identification) task is the intersection of the more familiar tasks of close-set identification and open-set verification/detection. In the multitarget detection task, an input of unknown class is processed by a bank of parallel detectors and a decision is required as to whether the input is from among the target classes and, if so, which one. In this...
متن کاملSpeaker verification on the world wide web
This paper describes a system for controlling access to web resources built using well-known speaker verification techniques. We describe the implementation of a speech verification server and an associated authentication module for the Apache web server. Speaker verification requires two inputs: a sample of the user’s speech and an identity claim for the user; typically the user’s name. Howeve...
متن کامل