S4-260152 - AI Proposals

[FS_ULBC] Analyzing semantic intelligibility in lossy coded audio signals

Back to Agenda Download Proposals
AI-Generated Proposals AI

Proposals

It is proposed to include the relevant content from Sections 3, 4, and 5 of this document into TR 26.940. This includes the methodology, experimental setup, and the analysis of results concerning the impact of audio bandwidth on semantic intelligibility, to capture the findings of this study.

Document Information
TDoc:
S4-260152
Source:
vivo Mobile Communication Co., Nokia, Xiaomi Technology, Samsung, Spreadtrum, Bytedance
Type:
pCR
For:
Agreement
Original Document:
View on 3GPP
Title: [FS_ULBC] Analyzing semantic intelligibility in lossy coded audio signals
Agenda item: 7.8
Agenda item description: FS_ULBC (Study on Ultra Low Bitrate Speech Codec)
Doc type: pCR
For action: Agreement
Abstract: This document presents the results of an experimental evaluation focusing on the semantic intelligibility of audio codecs under Ultra-Low Speech Bitrate (ULBC) [1] constraints. While traditional quality metrics often focus on perceptual quality (MOS), the primary objective of this paper is to quantify semantic preservation (the ability of the listener to accurately understand the spoken content) using automatic speech recognition (ASR) word error rate (WER) as a proxy.
Release: Rel-20
Specification: 26.94
Version: 0.4.0
Related WIs: FS_ULBC
Spec: 26.94
Contact: Wang Dong
Uploaded: 2026-02-03T13:43:09.937000
Contact ID: 107237
TDoc Status: noted
Reservation date: 03/02/2026 12:33:20
Agenda item sort order: 20