SpeechNet: A Universal Modularized Model for Speech Processing Tasks

05/07/2021
by   Yi-Chen Chen, et al.
16

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 3

page 14

11/13/2020

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...
11/04/2021

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

Speech intelligibility assessment models are essential tools for researc...
05/17/2016

Recurrent Neural Network for Text Classification with Multi-Task Learning

Neural network based methods have obtained great progress on a variety o...
05/18/2020

Efficient Image Gallery Representations at Scale Through Multi-Task Learning

Image galleries provide a rich source of diverse information about a pro...
08/29/2016

Learning and Inferring Relations in Cortical Networks

A pressing scientific challenge is to understand how brains work. Of par...
05/03/2021

SUPERB: Speech processing Universal PERformance Benchmark

Self-supervised learning (SSL) has proven vital for advancing research i...
11/19/2015

Patterns for Learning with Side Information

Supervised, semi-supervised, and unsupervised learning estimate a functi...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.