activity
20182022
most citedspeechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment

2 citations · 7 across the 10 of their papers we have counts for

collaborators
Showing cs.SDShow all

14 papers · 1 filter

cs.SD20221 cited

Improve Bilingual TTS Using Dynamic Language and Phonology Embedding

Fengyu Yang, Jian Luan, Yujun Wang

In most cases, bilingual TTS needs to handle three types of input scripts: first language only, second language only, and second language embedded in the first language. In the lat…

cs.SD2022

An empirical study of weakly supervised audio tagging embeddings for general audio representations

Heinrich Dinkel, Zhiyong Yan, Yongqing Wang +2

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of tran…

cs.SD20222 cited

UniKW-AT: Unified Keyword Spotting and Audio Tagging

Heinrich Dinkel, Yongqing Wang, Zhiyong Yan +2

Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical po…

cs.SD2022

Pseudo strong labels for large scale weakly supervised audio tagging

Heinrich Dinkel, Zhiyong Yan, Yongqing Wang +2

Large-scale audio tagging datasets inevitably contain imperfect labels, such as clip-wise annotated (temporally weak) tags with no exact on- and offsets, due to a high manual label…

cs.SD20221 cited

Learning Decoupling Features Through Orthogonality Regularization

Li Wang, Rongzhi Gu, Weiji Zhuang +3

Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independentl…

cs.SD20211 cited

A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting

Shenghua Hu, Jing Wang, Yujun Wang +2

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure go…