10 citations · 20 across the 12 of their papers we have counts for
14 papers
Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders
Jason Fong, Yun Wang, Prabhav Agrawal +4
Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording. Recent work has used neural models to produce edi…
GCT: Gated Contextual Transformer for Sequential Audio Tagging
Yuanbo Hou, Yun Wang, Wenwu Wang +1
Audio tagging aims to assign predefined tags to audio clips to indicate the class information of audio events. Sequential audio tagging (SAT) means detecting both the class informa…
CT-SAT: Contextual Transformer for Sequential Audio Tagging
Yuanbo Hou, Zhaoyi Liu, Bo Kang +2
Sequential audio event tagging can provide not only the type information of audio events, but also the order information between events and the number of events that occur in an au…
Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study
Dawei Liang, Yangyang Shi, Yun Wang +6
Detection of common events and scenes from audio is useful for extracting and understanding human contexts in daily life. Prior studies have shown that leveraging knowledge from a…
Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks
Sangeeta Srivastava, Yun Wang, Andros Tjandra +4
Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in…
Do sound event representations generalize to other audio tasks? A case study in audio transfer learning
Anurag Kumar, Yun Wang, Vamsi Krishna Ithapu +1
Transfer learning is critical for efficient information transfer across multiple related learning problems. A simple, yet effective transfer learning approach utilizes deep neural…
Dual Application of Speech Enhancement for Automatic Speech Recognition
Ashutosh Pandey, Chunxi Liu, Yun Wang +1
In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) f…
Power pooling: An adaptive pooling function for weakly labelled sound event detection
Yuzhuo Liu, Hangting Chen, YunWang +1
Access to large corpora with strongly labelled sound events is expensive and difficult in engineering applications. Much research turns to address the problem of how to detect both…
DELTA: A DEep learning based Language Technology plAtform
Kun Han, Junwen Chen, Hui Zhang +20
In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech pro…
Connectionist Temporal Localization for Sound Event Detection with Sequential Labeling
Yun Wang, Florian Metze
Research on sound event detection (SED) with weak labeling has mostly focused on presence/absence labeling, which provides no temporal information at all about the event occurrence…
A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling
Yun Wang, Juncheng Li, Florian Metze
Sound event detection (SED) entails two subtasks: recognizing what types of sound events are present in an audio stream (audio tagging), and pinpointing their onset and offset time…
Comparing the Max and Noisy-Or Pooling Functions in Multiple Instance Learning for Weakly Supervised Sequence Learning Tasks
Yun Wang, Juncheng Li, Florian Metze
Many sequence learning tasks require the localization of certain events in sequences. Because it can be expensive to obtain strong labeling that specifies the starting and ending t…
A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging
Juncheng Li, Yun Wang, Joseph Szurley +2
The lack of strong labels has severely limited the state-of-the-art fully supervised audio tagging systems to be scaled to larger dataset. Meanwhile, audio-visual learning models b…
Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection
Shao-Yen Tseng, Juncheng Li, Yun Wang +3
State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale da…