Voice cloning noisy audio: 10s vs 60s Mean Opinion Score (MOS) and Word Error Rate (WER)

Prefer 60-second noisy voice cloning only when its 95% MOS CI excludes zero and WER falls at least 1.0 absolute point; otherwise use 10 seconds or re-record. Independent technical note mirroring the canonical version: https://clonemyvoice.io/blog/voice-cloning-noisy-audio-10s-vs-60s-mean-opinion-score-mos-and-word-error-rate-wer.php

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-07
DOI
https://doi.org/10.5281/zenodo.24030917
Primary Topic
Speech Recognition and Synthesis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Voice cloning noisy audio: 10s vs 60s Mean Opinion Score (MOS) and Word Error Rate (WER)

Dylan Cooper
1 links
Zenodo (CERN European Organization for Nuclear Research)
Speech Recognition and Synthesis
preprint

Voice cloning noisy audio: 10s vs 60s Mean Opinion Score (MOS) and Word Error Rate (WER)

Dylan Cooper
preprint en

Abstract

Prefer 60-second noisy voice cloning only when its 95% MOS CI excludes zero and WER falls at least 1.0 absolute point; otherwise use 10 seconds or re-record. Independent technical note mirroring the canonical version: https://clonemyvoice.io/blog/voice-cloning-noisy-audio-10s-vs-60s-mean-opinion-score-mos-and-word-error-rate-wer.php

Zenodo (CERN European Organization for Nuclear Research)
Speech Recognition and Synthesis
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon