Alert button
Picture for Yujun Wang

Yujun Wang

Alert button

Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers

Mar 03, 2023
Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang

Figure 1 for Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Figure 2 for Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Figure 3 for Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Figure 4 for Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Viaarxiv icon

Improve Bilingual TTS Using Dynamic Language and Phonology Embedding

Dec 07, 2022
Fengyu Yang, Jian Luan, Yujun Wang

Figure 1 for Improve Bilingual TTS Using Dynamic Language and Phonology Embedding
Figure 2 for Improve Bilingual TTS Using Dynamic Language and Phonology Embedding
Figure 3 for Improve Bilingual TTS Using Dynamic Language and Phonology Embedding
Figure 4 for Improve Bilingual TTS Using Dynamic Language and Phonology Embedding
Viaarxiv icon

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

Sep 30, 2022
Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang

Figure 1 for An empirical study of weakly supervised audio tagging embeddings for general audio representations
Figure 2 for An empirical study of weakly supervised audio tagging embeddings for general audio representations
Figure 3 for An empirical study of weakly supervised audio tagging embeddings for general audio representations
Figure 4 for An empirical study of weakly supervised audio tagging embeddings for general audio representations
Viaarxiv icon

UniKW-AT: Unified Keyword Spotting and Audio Tagging

Sep 23, 2022
Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Junbo Zhang, Yujun Wang

Figure 1 for UniKW-AT: Unified Keyword Spotting and Audio Tagging
Figure 2 for UniKW-AT: Unified Keyword Spotting and Audio Tagging
Figure 3 for UniKW-AT: Unified Keyword Spotting and Audio Tagging
Figure 4 for UniKW-AT: Unified Keyword Spotting and Audio Tagging
Viaarxiv icon

Pseudo strong labels for large scale weakly supervised audio tagging

Apr 28, 2022
Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang

Figure 1 for Pseudo strong labels for large scale weakly supervised audio tagging
Figure 2 for Pseudo strong labels for large scale weakly supervised audio tagging
Figure 3 for Pseudo strong labels for large scale weakly supervised audio tagging
Figure 4 for Pseudo strong labels for large scale weakly supervised audio tagging
Viaarxiv icon

Learning Decoupling Features Through Orthogonality Regularization

Mar 31, 2022
Li Wang, Rongzhi Gu, Weiji Zhuang, Peng Gao, Yujun Wang, Yuexian Zou

Figure 1 for Learning Decoupling Features Through Orthogonality Regularization
Figure 2 for Learning Decoupling Features Through Orthogonality Regularization
Figure 3 for Learning Decoupling Features Through Orthogonality Regularization
Figure 4 for Learning Decoupling Features Through Orthogonality Regularization
Viaarxiv icon

Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation

Oct 19, 2021
Fengyu Yang, Jian Luan, Yujun Wang

Figure 1 for Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation
Figure 2 for Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation
Figure 3 for Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation
Figure 4 for Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation
Viaarxiv icon

PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control

Oct 09, 2021
Yunchao He, Jian Luan, Yujun Wang

Figure 1 for PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control
Figure 2 for PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control
Figure 3 for PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control
Figure 4 for PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control
Viaarxiv icon

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

Sep 01, 2021
Shenghua Hu, Jing Wang, Yujun Wang, Lidong Yang, Wenjing Yang

Figure 1 for A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting
Figure 2 for A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting
Figure 3 for A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting
Figure 4 for A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting
Viaarxiv icon

Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting

Aug 27, 2021
Shenghua Hu, Jing Wang, Yujun Wang, Wenjing Yang

Figure 1 for Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting
Figure 2 for Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting
Figure 3 for Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting
Figure 4 for Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting
Viaarxiv icon