当前位置:
X-MOL 学术
›
arXiv.cs.SD
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SpeechNet: A Universal Modularized Model for Speech Processing Tasks
arXiv - CS - Sound Pub Date : 2021-05-07 , DOI: arxiv-2105.03070 Yi-Chen Chen, Po-Han Chi, Shu-wen Yang, Kai-Wei Chang, Jheng-hao Lin, Sung-Feng Huang, Da-Rong Liu, Chi-Liang Liu, Cheng-Kuang Lee, Hung-yi Lee
arXiv - CS - Sound Pub Date : 2021-05-07 , DOI: arxiv-2105.03070 Yi-Chen Chen, Po-Han Chi, Shu-wen Yang, Kai-Wei Chang, Jheng-hao Lin, Sung-Feng Huang, Da-Rong Liu, Chi-Liang Liu, Cheng-Kuang Lee, Hung-yi Lee
There is a wide variety of speech processing tasks. For different tasks,
model networks are usually designed and tuned separately. This paper proposes a
universal modularized model, SpeechNet, which contains the five basic modules
for speech processing. The concatenation of modules solves a variety of speech
processing tasks. We select five important and common tasks in the experiments
that use all of these five modules altogether. Specifically, in each trial, we
jointly train a subset of all speech tasks under multi-task setting, with all
modules shared. Then we can observe whether one task can benefit another during
training. SpeechNet is modularized and flexible for incorporating more modules,
tasks, or training approaches in the future. We will release the code and
experimental settings to facilitate the research of modularized universal
models or multi-task learning of speech processing tasks.
中文翻译:
SpeechNet:用于语音处理任务的通用模块化模型
有各种各样的语音处理任务。对于不同的任务,模型网络通常是单独设计和调整的。本文提出了一个通用的模块化模型SpeechNet,其中包含语音处理的五个基本模块。模块的串联解决了各种语音处理任务。我们在实验中选择了五个重要且常见的任务,这些任务一并使用了这五个模块。具体来说,在每个试验中,我们在多任务设置下共同训练所有语音任务的子集,并共享所有模块。然后,我们可以观察到一项任务在培训期间是否可以使另一项受益。SpeechNet模块化且灵活,可以在将来合并更多的模块,任务或培训方法。
更新日期:2021-05-10
中文翻译:
SpeechNet:用于语音处理任务的通用模块化模型
有各种各样的语音处理任务。对于不同的任务,模型网络通常是单独设计和调整的。本文提出了一个通用的模块化模型SpeechNet,其中包含语音处理的五个基本模块。模块的串联解决了各种语音处理任务。我们在实验中选择了五个重要且常见的任务,这些任务一并使用了这五个模块。具体来说,在每个试验中,我们在多任务设置下共同训练所有语音任务的子集,并共享所有模块。然后,我们可以观察到一项任务在培训期间是否可以使另一项受益。SpeechNet模块化且灵活,可以在将来合并更多的模块,任务或培训方法。