A study on Mandarin broadcast news speech recognition

Abstract

In this paper, a basic Mandarin broadcast news speech recognition system is constructed using the MATBN database. It considers the acoustic modeling for Mandarin base-syllables, particles, and paralinguistic phenomena. It also considers environment-dependent acoustic modeling for three recording environments: studio anchors, outdoor reporters, and outdoor interviewee. Moreover, it incorporates a bigram language model with adaptation using data in MATBN. Syllable recognition rates of 89.64, 84.42 and 61.62% were achieved for the three environments of anchors, reporters and interviewees, respectively.