Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Qian, Kaizhi"'
Autor:
Ni, Junrui, Wang, Liming, Zhang, Yang, Qian, Kaizhi, Gao, Heting, Hasegawa-Johnson, Mark, Yoo, Chang D.
Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech and text dat
Externí odkaz:
http://arxiv.org/abs/2406.08380
Autor:
Chen, Jiaben, Yan, Xin, Chen, Yihang, Cen, Siyuan, Ma, Qinwei, Zhen, Haoyu, Qian, Kaizhi, Lu, Lie, Gan, Chuang
In this work, we introduce a challenging task for simultaneously generating 3D holistic body motions and singing vocals directly from textual lyrics inputs, advancing beyond existing works that typically address these two modalities in isolation. To
Externí odkaz:
http://arxiv.org/abs/2405.20336
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty, resulting
Externí odkaz:
http://arxiv.org/abs/2311.08718
Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more languages
Externí odkaz:
http://arxiv.org/abs/2306.15686
Modeling sounds emitted from physical object interactions is critical for immersive perceptual experiences in real and virtual worlds. Traditional methods of impact sound synthesis use physics simulation to obtain a set of physics parameters that cou
Externí odkaz:
http://arxiv.org/abs/2303.16897
Self-supervised learning (SSL) for rich speech representations has achieved empirical success in low-resource Automatic Speech Recognition (ASR) and other speech processing tasks, which can mitigate the necessity of a large amount of transcribed spee
Externí odkaz:
http://arxiv.org/abs/2211.01522
Autor:
Qian, Kaizhi, Zhang, Yang, Gao, Heting, Ni, Junrui, Lai, Cheng-I, Cox, David, Hasegawa-Johnson, Mark, Chang, Shiyu
Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks of SSL lear
Externí odkaz:
http://arxiv.org/abs/2204.09224
Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text examples, without the need for fine-tuning. Recent studies further show that
Externí odkaz:
http://arxiv.org/abs/2203.15863
Autor:
Ni, Junrui, Wang, Liming, Gao, Heting, Qian, Kaizhi, Zhang, Yang, Chang, Shiyu, Hasegawa-Johnson, Mark
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts w
Externí odkaz:
http://arxiv.org/abs/2203.15796
SpeechSplit can perform aspect-specific voice conversion by disentangling speech into content, rhythm, pitch, and timbre using multiple autoencoders in an unsupervised manner. However, SpeechSplit requires careful tuning of the autoencoder bottleneck
Externí odkaz:
http://arxiv.org/abs/2203.14156