From Senones to Chenones - Tied Context-Dependent Graphemes for Hybrid Speech Recognition.
ASRU, pp.457-464, (2019)
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence. In this work, we show for the first time that, on English, hyb...更多
下载 PDF 全文