138 citations · 792 across the 57 of their papers we have counts for
13 papers · 1 filter
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Zehua Chen, Yihan Wu, Yichong Leng +9
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, the…
Ontology-aware Learning and Evaluation for Audio Tagging
Haohe Liu, Qiuqiang Kong, Xubo Liu +3
This study defines a new evaluation metric for audio tagging tasks to overcome the limitation of the conventional mean average precision (mAP) metric, which treats different kinds…
Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention
Xubo Liu, Qiushi Huang, Xinhao Mei +10
Audio captioning aims to generate text descriptions of audio clips. In the real world, many objects produce similar sounds. How to accurately recognize ambiguous sounds is a major…
Learning Temporal Resolution in Spectrogram for Audio Classification
Haohe Liu, Xubo Liu, Qiuqiang Kong +2
The audio spectrogram is a time-frequency representation that has been widely used for audio classification. One of the key attributes of the audio spectrogram is the temporal reso…
Simple Pooling Front-ends For Efficient Audio Classification
Xubo Liu, Haohe Liu, Qiuqiang Kong +3
Recently, there has been increasing interest in building efficient audio neural networks for on-device scenarios. Most existing approaches are designed to reduce the size of audio…
Surrey System for DCASE 2022 Task 5: Few-shot Bioacoustic Event Detection with Segment-level Metric Learning
Haohe Liu, Xubo Liu, Xinhao Mei +3
Few-shot audio event detection is a task that detects the occurrence time of a novel sound class given a few examples. In this work, we propose a system based on segment-level metr…
Segment-level Metric Learning for Few-shot Bioacoustic Event Detection
Haohe Liu, Xubo Liu, Xinhao Mei +3
Few-shot bioacoustic event detection is a task that detects the occurrence time of a novel sound given a few examples. Previous methods employ metric learning to build a latent spa…
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
Xu Tan, Jiawei Chen, Haohe Liu +11
Text to speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality…
BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
Yichong Leng, Zehua Chen, Junliang Guo +9
Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing the…
VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration
Haohe Liu, Xubo Liu, Qiuqiang Kong +5
Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on a single type of distortion, such as speech denoising or dereverberation. However, sp…
Separate What You Describe: Language-Queried Audio Source Separation
Xubo Liu, Haohe Liu, Qiuqiang Kong +5
In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language qu…
Neural Vocoder is All You Need for Speech Super-resolution
Haohe Liu, Woosung Choi, Xubo Liu +3
Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental…
Leveraging Pre-trained BERT for Audio Captioning
Xubo Liu, Xinhao Mei, Qiushi Huang +6
Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture,…