Autoregressive Predictive Coding: A Comprehensive Study

We review autoregressive predictive coding (APC), an approach to learn speech representation by predicting a future frame given the past frames. We present three different views of interpreting APC, and provide a historical account to the approach. To study the speech representation learned by APC,...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in signal processing 2022-10, Vol.16 (6), p.1380-1390
Main Authors: Yang, Gene-Ping, Yeh, Sung-Lin, Chung, Yu-An, Glass, James, Tang, Hao
Format: Article
Language:English
Subjects:
Algorithms
Automatic speech recognition
Autoregressive processes
Classification
Coding
Fundamental frequency
Linguistics
Phonetics
Predictive coding
Prosody
Representation learning
Representations
Resonant frequencies
Self-supervised learning
Speaker identification
speaker verification
Speech recognition
Voice recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We review autoregressive predictive coding (APC), an approach to learn speech representation by predicting a future frame given the past frames. We present three different views of interpreting APC, and provide a historical account to the approach. To study the speech representation learned by APC, we use common speech tasks, such as automatic speech recognition and speaker verification, to demonstrate the utility of the learned representation. In addition, we design a suite of fine-grained tasks, including frame classification, segment classification, fundamental frequency tracking, and duration prediction, to probe the phonetic and prosodic content of the representation. The three views of the APC objective welcome various generalizations and algorithms to learn speech representations. Probing on the suite of fine-grained tasks suggests that APC makes a wide range of high-level speech information accessible in its learned representation.
ISSN:1932-4553
1941-0484
DOI:10.1109/JSTSP.2022.3203608