Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Violeta, Lester Phillip, Huang, Wen-Chin, Ma, Ding, Yamamoto, Ryuichi, Kobayashi, Kazuhiro, Toda, Tomoki
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913201626546176
author Violeta, Lester Phillip
Huang, Wen-Chin
Ma, Ding
Yamamoto, Ryuichi
Kobayashi, Kazuhiro
Toda, Tomoki
author_facet Violeta, Lester Phillip
Huang, Wen-Chin
Ma, Ding
Yamamoto, Ryuichi
Kobayashi, Kazuhiro
Toda, Tomoki
contents We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have proven to work well in this task, but in most cases, various mismatches, such as the speech type mismatch (electrolaryngeal vs. typical) or a speaker mismatch between the datasets used in each stage, can deteriorate the conversion performance of this framework. To resolve this issue, we propose a linguistic encoder robust enough to project both EL and typical speech in the same latent space, while still being able to extract accurate linguistic information, creating a unified representation to reduce the speech type mismatch. Furthermore, we introduce HuBERT output features to the proposed framework for reducing the speaker mismatch, making it possible to effectively use a large-scale parallel dataset during pretraining. We show that compared to the conventional framework using mel-spectrogram input and output features, using the proposed framework enables the model to synthesize more intelligible and naturally sounding speech, as shown by a significant 16% improvement in character error rate and 0.83 improvement in naturalness score.
format Preprint
id arxiv_https___arxiv_org_abs_2309_09627
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders
Violeta, Lester Phillip
Huang, Wen-Chin
Ma, Ding
Yamamoto, Ryuichi
Kobayashi, Kazuhiro
Toda, Tomoki
Sound
Audio and Speech Processing
We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have proven to work well in this task, but in most cases, various mismatches, such as the speech type mismatch (electrolaryngeal vs. typical) or a speaker mismatch between the datasets used in each stage, can deteriorate the conversion performance of this framework. To resolve this issue, we propose a linguistic encoder robust enough to project both EL and typical speech in the same latent space, while still being able to extract accurate linguistic information, creating a unified representation to reduce the speech type mismatch. Furthermore, we introduce HuBERT output features to the proposed framework for reducing the speaker mismatch, making it possible to effectively use a large-scale parallel dataset during pretraining. We show that compared to the conventional framework using mel-spectrogram input and output features, using the proposed framework enables the model to synthesize more intelligible and naturally sounding speech, as shown by a significant 16% improvement in character error rate and 0.83 improvement in naturalness score.
title Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2309.09627