39 citations · 132 across the 28 of their papers we have counts for
7 papers · 1 filter
Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language
Turi Abu, Ying Shi, Thomas Fang Zheng +1
We present a novel Automatic Speech Recognition (ASR) dataset for the Oromo language, a widely spoken language in Ethiopia and neighboring regions. The dataset was collected throug…
Enhanced Neural Machine Translation by Learning from Draft
Aodong Li, Shiyue Zhang, Dong Wang +1
Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left t…
System Combination for Short Utterance Speaker Recognition
Lantian Li, Dong Wang, Xiaodong Zhang +2
For text-independent short-utterance speaker recognition (SUSR), the performance often degrades dramatically. This paper presents a combination approach to the SUSR tasks with two…
Transfer Learning for Speech and Language Processing
Dong Wang, Thomas Fang Zheng
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trai…
Deep Speaker Vectors for Semi Text-independent Speaker Verification
Lantian Li, Dong Wang, Zhiyong Zhang +1
Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker veri…
Distant Supervision for Entity Linking
Miao Fan, Qiang Zhou, Thomas Fang Zheng
Entity linking is an indispensable operation of populating knowledge repositories for information extraction. It studies on aligning a textual entity mention to its corresponding d…
Errata: Distant Supervision for Relation Extraction with Matrix Completion
Miao Fan, Deli Zhao, Qiang Zhou +3
The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features. To tackle the sparsity and no…