Call-type classification and unsupervised training for the call center domain

Abstract

We describe recent experiments in call-type classification and acoustic modeling for speech recognition in the call center domain. We first describe the CU Call Center Corpus, a database of human-to-human conversations recorded from an information technology (IT) help desk call center located on the University of Colorado campus. Next, we describe our analysis and labeling of the recorded conversations into a hierarchical taxonomy of the call types. We consider four methods for call-type classification and provide initial experiments illustrating classification error rates for this new task domain. It is shown that lightly supervised training based on using the output from an automatic speech recognizer in conjunction with supervised labeling of calls by call-type can substantially reduce classification error rates and development efforts when only limited training data are available. A call-type classification error rate of 24% is achieved using a classifier based on support vector machines. Finally, we consider issues related to unsupervised acoustic and language model training for improved call transcription and point to directions for future work.