Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Subramani, Krishna, Valin, Jean-Marc, Buethe, Jan, Smaragdis, Paris, Goodwin, Mike
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914641171447808
author Subramani, Krishna
Valin, Jean-Marc
Buethe, Jan
Smaragdis, Paris
Goodwin, Mike
author_facet Subramani, Krishna
Valin, Jean-Marc
Buethe, Jan
Smaragdis, Paris
Goodwin, Mike
contents Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement. Recently, pitch estimators based on deep neural networks (DNNs) have have been outperforming well-established DSP-based techniques. Unfortunately, these new estimators can be impractical to deploy in real-time systems, both because of their relatively high complexity, and the fact that some require significant lookahead. We show that a hybrid estimator using a small deep neural network (DNN) with traditional DSP-based features can match or exceed the performance of pure DNN-based models, with a complexity and algorithmic delay comparable to traditional DSP-based algorithms. We further demonstrate that this hybrid approach can provide benefits for a neural vocoding task.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14507
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
Subramani, Krishna
Valin, Jean-Marc
Buethe, Jan
Smaragdis, Paris
Goodwin, Mike
Audio and Speech Processing
Sound
Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement. Recently, pitch estimators based on deep neural networks (DNNs) have have been outperforming well-established DSP-based techniques. Unfortunately, these new estimators can be impractical to deploy in real-time systems, both because of their relatively high complexity, and the fact that some require significant lookahead. We show that a hybrid estimator using a small deep neural network (DNN) with traditional DSP-based features can match or exceed the performance of pure DNN-based models, with a complexity and algorithmic delay comparable to traditional DSP-based algorithms. We further demonstrate that this hybrid approach can provide benefits for a neural vocoding task.
title Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2309.14507