# Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition

arXiv: https://arxiv.org/abs/2512.07005 · HTML: https://mlsanity.com/paper/2512.07005/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus](https://mlsanity.com/paper/2112.10358/) (2021)
- [JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis](https://mlsanity.com/paper/1711.00354/) (2017)
- [Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis](https://mlsanity.com/paper/2201.07429/) (2022)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [DiDiSpeech: A Large Scale Mandarin Speech Corpus](https://mlsanity.com/paper/2010.09275/) (2020)
- [CN-Celeb: multi-genre speaker recognition](https://mlsanity.com/paper/2012.12468/) (2020)
- [The Singing Voice Conversion Challenge 2023](https://mlsanity.com/paper/2306.14422/) (2023)
- [MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music](https://mlsanity.com/paper/2402.09871/) (2024)
- [JVS-MuSiC: Japanese multispeaker singing-voice corpus](https://mlsanity.com/paper/2001.07044/) (2020)
- [SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias](https://mlsanity.com/paper/2209.06054/) (2022)
- [Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis](https://mlsanity.com/paper/2205.04029/) (2022)
- [SketchFFusion: Sketch-guided image editing with diffusion model](https://mlsanity.com/paper/2304.03174/) (2023)
- [REMAST: Real-time Emotion-based Music Arrangement with Soft Transition](https://mlsanity.com/paper/2305.08029/) (2023)
- [SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement](https://mlsanity.com/paper/2407.07728/) (2024)
- [Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition](https://mlsanity.com/paper/2311.07062/) (2023)
- [Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition](https://mlsanity.com/paper/2407.03026/) (2024)

## Built on by (most cited first, 1 of 1)

- [VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition](https://mlsanity.com/paper/2607.27768/) (2026)

## Abstract (arXiv)

Singing accent research is underexplored compared to speech accent studies, primarily due to the scarcity of suitable datasets. Existing singing datasets often suffer from detail loss, frequently resulting from the vocal-instrumental separation process. Additionally, they often lack regional accent annotations. To address this, we introduce the Multi-Accent Mandarin Dry-Vocal Singing Dataset (MADVSD). MADVSD comprises over 670 hours of dry vocal recordings from 4,206 native Mandarin speakers across nine distinct Chinese regions. In addition to each participant recording audio of three popular songs in their native accent, they also recorded phonetic exercises covering all Mandarin vowels and a full octave range. We validated MADVSD through benchmark experiments in singing accent recognition, demonstrating its utility for evaluating state-of-the-art speech models in singing contexts. Furthermore, we explored dialectal influences on singing accent and analyzed the role of vowels in accentual variations, leveraging MADVSD's unique phonetic exercises.