SpeechNet: A Universal Modularized Model for Speech Processing Tasks

by   Yi-Chen Chen, et al.

There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal model can perform multiple speech processing tasks, some tasks might be improved with the related abilities learned from other tasks. The multi-task learning of a wide variety of speech processing tasks with a universal model has not been studied. This paper proposes a universal modularized model, SpeechNet, which treats all speech processing tasks into a speech/text input and speech/text output format. We select five essential speech processing tasks for multi-task learning experiments with SpeechNet. We show that SpeechNet learns all of the above tasks, and we further analyze which tasks can be improved by other tasks. SpeechNet is modularized and flexible for incorporating more modules, tasks, or training approaches in the future. We release the code and experimental settings to facilitate the research of modularized universal models and multi-task learning of speech processing tasks.


page 2

page 3

page 14


Re-framing Incremental Deep Language Models for Dialogue Processing with Multi-task Learning

We present a multi-task learning framework to enable the training of one...

Multi-task learning of speech and speaker recognition

We study multi-task learning for two orthogonal speech technology tasks:...

InQSS: a speech intelligibility assessment model using a multi-task learning network

Speech intelligibility assessment models are essential tools for researc...

MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning

With the growth of computer vision applications, deep learning, and edge...

Improving Multi-task Learning via Seeking Task-based Flat Regions

Multi-Task Learning (MTL) is a widely-used and powerful learning paradig...

Learning and Inferring Relations in Cortical Networks

A pressing scientific challenge is to understand how brains work. Of par...

Efficient Image Gallery Representations at Scale Through Multi-Task Learning

Image galleries provide a rich source of diverse information about a pro...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset