261 citations · 273 across the 6 of their papers we have counts for
6 papers
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…
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…
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…
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…
Topic Identification for Speech without ASR
Chunxi Liu, Jan Trmal, Matthew Wiesner +2
Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR ou…
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…