arXiv 2409.140852024-09-21eess.AScs.SD

Codec-SUPERB @ SLT 2024：面向神经音频编解码器模型的轻量级基准测试

Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models

National Taiwan University（台湾大学）；Massachusetts Institute of Technology（麻省理工学院）；Microsoft Corporation（微软公司）；Meta；The Chinese University of Hong Kong（香港中文大学）；Carnegie Mellon University（卡内基梅隆大学）

Haibin Wu, Xuanjun Chen, Yi-Cheng Lin, Kaiwei Chang, Jiawei Du, Ke-Han Lu, Alexander H. Liu, Ho-Lam Chung, Yuan-Kuei Wu, Dongchao Yang, Songxiang Liu, Yi-Chiao … 展开作者

Haibin Wu, Xuanjun Chen, Yi-Cheng Lin, Kaiwei Chang, Jiawei Du, Ke-Han Lu, Alexander H. Liu, Ho-Lam Chung, Yuan-Kuei Wu, Dongchao Yang, Songxiang Liu, Yi-Chiao Wu, Xu Tan, James Glass, Shinji Watanabe, Hung-yi Lee

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文介绍了SLT 2024的Codec-SUPERB挑战赛，通过提供统一的语音应用、客观指标和小规模免许可数据集，实现对神经音频编解码器模型公平且轻量级的评估，并报告了五个参赛系统的结果与发现。

摘要：

神经音频编解码器模型正变得越来越重要，因为它们作为音频的 tokenizer，能够实现高效传输或促进语音语言建模。理想的神经音频编解码器即使在低比特率下也应保持内容、副语言学、说话人特征和音频信息。最近，人们提出了许多先进的神经编解码器模型。然而，编解码器模型往往在不同的实验条件下进行测试。因此，我们在 SLT 2024 上引入了 Codec-SUPERB 挑战赛，旨在促进现有编解码器模型之间公平且轻量级的比较，并激发该领域的进步。该挑战赛汇集了具有代表性的语音应用和客观指标，并仔细挑选了免许可的数据集，将其采样为小集合以降低评估计算成本。本文介绍了该挑战赛的规则、数据集、五个参赛系统、结果和发现。

英文摘要：

Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The ideal neural audio codec should maintain content, paralinguistics, speaker characteristics, and audio information even at low bitrates. Recently, numerous advanced neural codec models have been proposed. However, codec models are often tested under varying experimental conditions. As a result, we introduce the Codec-SUPERB challenge at SLT 2024, designed to facilitate fair and lightweight comparisons among existing codec models and inspire advancements in the field. This challenge brings together representative speech applications and objective metrics, and carefully selects license-free datasets, sampling them into small sets to reduce evaluation computation costs. This paper presents the challenge's rules, datasets, five participant systems, results, and findings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。