MCE 2018: The 1st Multi-target Speaker Detection and Identification Challenge Evaluation (MCE) Plan, Dataset and Baseline System
This addresses the need for improved speaker verification in security and call center applications, but it is incremental as it builds on existing i-vector methods.
The paper tackles the problem of multi-target speaker detection and identification in real-world telephone conversations, introducing a challenge, dataset, and baseline system to evaluate accuracy in detecting blacklisted speakers and identifying specific individuals.
The Multitarget Challenge aims to assess how well current speech technology is able to determine whether or not a recorded utterance was spoken by one of a large number of 'blacklisted' speakers. It is a form of multi-target speaker detection based on real-world telephone conversations. Data recordings are generated from call center customer-agent conversations. Each conversation is represented by a single i-vector. Given a pool of training and development data from non-Blacklist and Blacklist speakers, the task is to measure how accurately one can detect 1) whether a test recording is spoken by a Blacklist speaker, and 2) which specific Blacklist speaker was talking.