VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Jiatong, Shim, Hye-jin, Tian, Jinchuan, Arora, Siddhant, Wu, Haibin, Petermann, Darius, Yip, Jia Qi, Zhang, You, Tang, Yuxun, Zhang, Wangyou, Alharthi, Dareen Safar, Huang, Yichen, Saito, Koichi, Han, Jionghao, Zhao, Yiwen, Donahue, Chris, Watanabe, Shinji
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916663333486592
author Shi, Jiatong
Shim, Hye-jin
Tian, Jinchuan
Arora, Siddhant
Wu, Haibin
Petermann, Darius
Yip, Jia Qi
Zhang, You
Tang, Yuxun
Zhang, Wangyou
Alharthi, Dareen Safar
Huang, Yichen
Saito, Koichi
Han, Jionghao
Zhao, Yiwen
Donahue, Chris
Watanabe, Shinji
author_facet Shi, Jiatong
Shim, Hye-jin
Tian, Jinchuan
Arora, Siddhant
Wu, Haibin
Petermann, Darius
Yip, Jia Qi
Zhang, You
Tang, Yuxun
Zhang, Wangyou
Alharthi, Dareen Safar
Huang, Yichen
Saito, Koichi
Han, Jionghao
Zhao, Yiwen
Donahue, Chris
Watanabe, Shinji
contents In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for various speech, audio, and music signals. The toolkit features a Pythonic interface with flexible configuration and dependency control, making it user-friendly and efficient. With full installation, VERSA offers 65 metrics with 729 metric variations based on different configurations. These metrics encompass evaluations utilizing diverse external resources, including matching and non-matching reference audio, text transcriptions, and text captions. As a lightweight yet comprehensive toolkit, VERSA is versatile to support the evaluation of a wide range of downstream scenarios. To demonstrate its capabilities, this work highlights example use cases for VERSA, including audio coding, speech synthesis, speech enhancement, singing synthesis, and music generation. The toolkit is available at https://github.com/wavlab-speech/versa.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17667
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music
Shi, Jiatong
Shim, Hye-jin
Tian, Jinchuan
Arora, Siddhant
Wu, Haibin
Petermann, Darius
Yip, Jia Qi
Zhang, You
Tang, Yuxun
Zhang, Wangyou
Alharthi, Dareen Safar
Huang, Yichen
Saito, Koichi
Han, Jionghao
Zhao, Yiwen
Donahue, Chris
Watanabe, Shinji
Sound
Multimedia
Audio and Speech Processing
In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for various speech, audio, and music signals. The toolkit features a Pythonic interface with flexible configuration and dependency control, making it user-friendly and efficient. With full installation, VERSA offers 65 metrics with 729 metric variations based on different configurations. These metrics encompass evaluations utilizing diverse external resources, including matching and non-matching reference audio, text transcriptions, and text captions. As a lightweight yet comprehensive toolkit, VERSA is versatile to support the evaluation of a wide range of downstream scenarios. To demonstrate its capabilities, this work highlights example use cases for VERSA, including audio coding, speech synthesis, speech enhancement, singing synthesis, and music generation. The toolkit is available at https://github.com/wavlab-speech/versa.
title VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music
topic Sound
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2412.17667