Search Results - "Song, Xuchen"

High-Resolution Piano Transcription With Pedals by Regressing Onset and Offset Times by Kong, Qiuqiang, Li, Bochen, Song, Xuchen, Wan, Yuan, Wang, Yuxuan

“…Automatic music transcription (AMT) is the task of transcribing audio recordings into symbolic representations. Recently, neural network-based methods have…”
Get full text

A handwritten Chinese characters recognition method based on sample set expansion and CNN by Xuchen Song, Xue Gao, Yanfang Ding, Zhixin Wang

“…Convolutional neural networks (CNN) is a powerful technology for classification of visual inputs. However, both the scale and quality of the training set are…”
Get full text

Source Separation with Weakly Labelled Data: an Approach to Computational Auditory Scene Analysis by Kong, Qiuqiang, Wang, Yuxuan, Song, Xuchen, Cao, Yin, Wang, Wenwu, Plumbley, Mark D.

“…Source separation is the task of separating an audio recording into individual sound sources. Source separation is fundamental for computational auditory scene…”
Get full text

Visual Working Memory Organizes Functional Related Objects beyond the Spatiotemporal Limit by Duan, Ziyi, Song, Xuchen, Shui, Rende, Zhou, Jifan, Shen, Mowei, Ding, Xiaowei

Get full text

Modeling Beats and Downbeats with a Time-Frequency Transformer by Hung, Yun-Ning, Wang, Ju-Chiang, Song, Xuchen, Lu, Wei-Tsung, Won, Minz

“…Transformer is a successful deep neural network (DNN) architecture that has shown its versatility not only in natural language processing but also in music…”
Get full text

A Neural Network Based Ranking Framework to Improve ASR with NLU Related Knowledge Deployed by Zhou, Zhengyu, Song, Xuchen, Botros, Rami, Zhao, Lin

“…This work proposes a new neural network framework to simultaneously rank multiple hypotheses generated by one or more automatic speech recognition (ASR)…”
Get full text

Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-Task Learning by Wang, Ju-Chiang, Smith, Jordan B.L., Chen, Jitong, Song, Xuchen, Wang, Yuxuan

“…This paper presents a novel supervised approach to detecting the chorus segments in popular music. Traditional approaches to this task are mostly unsupervised,…”
Get full text

A Long-Tail Friendly Representation Framework for Artist and Music Similarity by Xiang, Haoran, Dai, Junyu, Song, Xuchen, Shen, Furao

“…The investigation of the similarity between artists and music is crucial in music retrieval and recommendation, and addressing the challenge of the long-tail…”
Get full text

Music Era Recognition Using Supervised Contrastive Learning and Artist Information by He, Qiqi, Song, Xuchen, Hao, Weituo, Wang, Ju-Chiang, Lu, Wei-Tsung, Li, Wei

“…Does popular music from the 60s sound different than that of the 90s? Prior study has shown that there would exist some variations of patterns and regularities…”
Get full text

ALCAP: Alignment-Augmented Music Captioner by He, Zihao, Hao, Weituo, Lu, Wei-Tsung, Chen, Changyou, Lerman, Kristina, Song, Xuchen

“…Music captioning has gained significant attention in the wake of the rising prominence of streaming media platforms. Traditional approaches often prioritize…”
Get full text

CatNet: music source separation system with mix-audio augmentation by Song, Xuchen, Kong, Qiuqiang, Du, Xingjian, Wang, Yuxuan

“…Music source separation (MSS) is the task of separating a music piece into individual sources, such as vocals and accompaniment. Recently, neural network based…”
Get full text

InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models by Han, Bing, Dai, Junyu, Hao, Weituo, He, Xinyan, Guo, Dong, Chen, Jitong, Wang, Yuxuan, Qian, Yanmin, Song, Xuchen

“…Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece…”
Get full text

High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times by Kong, Qiuqiang, Li, Bochen, Song, Xuchen, Wan, Yuan, Wang, Yuxuan

“…Automatic music transcription (AMT) is the task of transcribing audio recordings into symbolic representations. Recently, neural network-based methods have…”
Get full text

Modeling Beats and Downbeats with a Time-Frequency Transformer by Hung, Yun-Ning, Wang, Ju-Chiang, Song, Xuchen, Lu, Wei-Tsung, Won, Minz

“…Transformer is a successful deep neural network (DNN) architecture that has shown its versatility not only in natural language processing but also in music…”
Get full text

SpecTNT: a Time-Frequency Transformer for Music Audio by Lu, Wei-Tsung, Wang, Ju-Chiang, Won, Minz, Choi, Keunwoo, Song, Xuchen

“…International Society for Music Information Retrieval (ISMIR) 2021 Transformers have drawn attention in the MIR field for their remarkable performance shown in…”
Get full text

Supervised Metric Learning for Music Structure Features by Wang, Ju-Chiang, Smith, Jordan B. L, Lu, Wei-Tsung, Song, Xuchen

“…Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length…”
Get full text

Efficient Neural Music Generation by Lam, Max W. Y, Tian, Qiao, Li, Tang, Yin, Zongyu, Feng, Siyuan, Tu, Ming, Ji, Yuliang, Xia, Rui, Ma, Mingbo, Song, Xuchen, Chen, Jitong, Wang, Yuping, Wang, Yuxuan

“…Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for…”
Get full text

Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-task Learning by Wang, Ju-Chiang, Smith, Jordan B. L, Chen, Jitong, Song, Xuchen, Wang, Yuxuan

“…This paper presents a novel supervised approach to detecting the chorus segments in popular music. Traditional approaches to this task are mostly unsupervised,…”
Get full text

Modeling the Compatibility of Stem Tracks to Generate Music Mashups by Huang, Jiawen, Wang, Ju-Chiang, Smith, Jordan B. L, Song, Xuchen, Wang, Yuxuan

“…A music mashup combines audio elements from two or more songs to create a new work. To reduce the time and effort required to make them, researchers have…”
Get full text

Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement by Dai, Dongyang, Chen, Li, Wang, Yuping, Wang, Mu, Xia, Rui, Song, Xuchen, Wu, Zhiyong, Wang, Yuxuan

“…With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in…”
Get full text