activity
20172019
most citedAn Empirical Evaluation of Zero Resource Acoustic Unit Discovery

4 citations · 4 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CL2019

Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks

Andros Tjandra, Chunxi Liu, Frank Zhang +5

Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to f…

cs.CL2019

Transformer-based Acoustic Modeling for Hybrid Speech Recognition

Yongqiang Wang, Abdelrahman Mohamed, Duc Le +10

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional emb…

cs.CL2018

Low-Resource Contextual Topic Identification on Speech

Chunxi Liu, Matthew Wiesner, Shinji Watanabe +4

In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is indepe…

cs.CL2018

Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

Matthew Wiesner, Chunxi Liu, Lucas Ondel +6

Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While…

cs.CL20174 cited

An Empirical Evaluation of Zero Resource Acoustic Unit Discovery

Chunxi Liu, Jinyi Yang, Ming Sun +7

Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations. A…