Oct, 2018
基于语音和文本数据的音位结构学习,较少资源近乎无监督的语音识别
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data
Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang, Hung-yi Lee, Lin-shan Lee
TL;DR利用音频字向量和自编码器实现跨模态的语音识别,演示了即使缺乏训练数据,也可以从少量音频和文本之间的嵌入对齐中进行 ASR 系统的训练。