Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word segmentation that might lead to erroneous speech recognition output. We propose pronunciation-assisted sub-word modeling (PASM), a sub-word extraction method that leverages the pronunciation information of a word. Experiments show that the proposed method can greatly improve upon the character-based baseline, and also outperform commonly used byte-pair encoding methods.
翻译:多数端对端语音识别系统示范文本直接作为字符或子字的顺序。目前对小字提取方法只考虑字符顺序频率,这些频率有时产生低劣的子字区分,可能导致错误的语音识别输出。我们建议采用读音辅助小词模型(PASM),这是一种小字提取方法,利用一个字的读音信息。实验显示,拟议方法可以大大改进基于字符的基准,并且也优于常用的字节编码方法。