1. L-vector: Neural label embed-ding for domain adaptation;meng;Proc ICASSP,0
2. Large scale deep neu-ral network acoustic modeling with semi-supervised training data for youtube video transcription;liao;Proc ASRU IEEE,0
3. Speaker adaptation of context dependent deep neural networks
4. Recognizing Long-Form Speech Using Streaming End-to-End Models
5. Learning small-size DNN with output-distribution-based criteria;li;InterSpeech,2014