A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Geng, Haopeng, Saito, Daisuke, Minematsu, Nobuaki
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917793607188480
author Geng, Haopeng
Saito, Daisuke
Minematsu, Nobuaki
author_facet Geng, Haopeng
Saito, Daisuke
Minematsu, Nobuaki
contents Utterances by L2 speakers can be unintelligible due to mispronunciation and improper prosody. In computer-aided language learning systems, textual feedback is often provided using a speech recognition engine. However, an ideal form of feedback for L2 speakers should be so fine-grained that it enables them to detect and diagnose unintelligible parts of L2 speakers' utterances. Inspired by language teachers who correct students' pronunciation through a voice-to-voice process, this pilot study utilizes a unique semi-parallel dataset composed of non-native speakers' (L2) reading aloud, shadowing of native speakers (L1) and their script-shadowing utterances. We explore the technical possibility of replicating the process of an L1 speaker's shadowing L2 speech using Voice Conversion techniques, to create a virtual shadower system. Experimental results demonstrate the feasibility of the VC system in simulating L1's shadowing behavior. The output of the virtual shadower system shows a reasonable similarity to the real L1 shadowing utterances in both linguistic and acoustic aspects.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02239
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings
Geng, Haopeng
Saito, Daisuke
Minematsu, Nobuaki
Sound
Computation and Language
Audio and Speech Processing
Utterances by L2 speakers can be unintelligible due to mispronunciation and improper prosody. In computer-aided language learning systems, textual feedback is often provided using a speech recognition engine. However, an ideal form of feedback for L2 speakers should be so fine-grained that it enables them to detect and diagnose unintelligible parts of L2 speakers' utterances. Inspired by language teachers who correct students' pronunciation through a voice-to-voice process, this pilot study utilizes a unique semi-parallel dataset composed of non-native speakers' (L2) reading aloud, shadowing of native speakers (L1) and their script-shadowing utterances. We explore the technical possibility of replicating the process of an L1 speaker's shadowing L2 speech using Voice Conversion techniques, to create a virtual shadower system. Experimental results demonstrate the feasibility of the VC system in simulating L1's shadowing behavior. The output of the virtual shadower system shows a reasonable similarity to the real L1 shadowing utterances in both linguistic and acoustic aspects.
title A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2410.02239