Work

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

Year: 2026

Type: preprint

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

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.24030917

Author: Cooper, Dylan

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7225459291

Cites:

Cited by:

Related to: 10