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

• URL: http://arxiv.org/abs/2512.07005v1
• Date: Sun, 07 Dec 2025 21:14:26 GMT
• Title: Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition
• Abstract summary: MADVSD comprises over 670 hours of dry vocal recordings from 4,206 native Mandarin speakers across nine distinct Chinese regions.<n>We validated MADVSD through benchmark experiments in singing accent recognition.<n>We explored dialectal influences on singing accent and analyzed the role of vowels in accentual variations.
• Score: 28.382926227472026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Vocal Music under Phoneme-Conditional Analysis [29.619759892670306]
  We use phoneme-conditional analysis to study the acoustic effect of typologically distinctive phonemes.<n>Across nine typologically diverse languages and thousands of songs, we measure effects along five acoustic dimensions.<n>Our findings suggest that phonological structure leaves measurable traces in how each language is sung.
  arXiv  Detail & Related papers  (2026-08-31T14:03:36Z)
• GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks [52.30565320125514]
  GTSinger is a large global, multi-technique, free-to-use, high-quality singing corpus with realistic music scores.<n>We collect 80.59 hours of high-quality singing voices, forming the largest recorded singing dataset.<n>We conduct four benchmark experiments: technique-controllable singing voice synthesis, technique recognition, style transfer, and speech-to-singing conversion.
  arXiv  Detail & Related papers  (2024-09-20T18:18:14Z)
• Singer Identity Representation Learning using Self-Supervised Techniques [0.0]
  We propose a framework for training singer identity encoders to extract representations suitable for various singing-related tasks. We explore different self-supervised learning techniques on a large collection of isolated vocal tracks. We evaluate the quality of the resulting representations on singer similarity and identification tasks.
  arXiv  Detail & Related papers  (2024-01-10T10:41:38Z)
• Accented Speech Recognition With Accent-specific Codebooks [53.288874858671576]
  Speech accents pose a significant challenge to state-of-the-art automatic speech recognition (ASR) systems. Degradation in performance across underrepresented accents is a severe deterrent to the inclusive adoption of ASR. We propose a novel accent adaptation approach for end-to-end ASR systems using cross-attention with a trainable set of codebooks.
  arXiv  Detail & Related papers  (2023-10-24T16:10:58Z)
• A study on native American English speech recognition by Indian listeners with varying word familiarity level [62.14295630922855]
  We have three kinds of responses from each listener while they recognize an utterance. From these transcriptions, word error rate (WER) is calculated and used as a metric to evaluate the similarity between the recognized and the original sentences. Speaker nativity wise analysis shows that utterances from speakers of some nativity are more difficult to recognize by Indian listeners compared to few other nativities.
  arXiv  Detail & Related papers  (2021-12-08T07:43:38Z)
• Synchronising speech segments with musical beats in Mandarin and English singing [4.627414193046309]
  The presence of musical beats was more dependent on segment duration than sonority. Mandarin and English demonstrated cross-linguistic variations despite exhibiting common patterns.
  arXiv  Detail & Related papers  (2021-06-18T10:32:27Z)
• Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties [77.2347265289855]
  We focus on phoneme recognition using Allosaurus, a method for multilingual recognition based on phonetic annotation. To evaluate in a challenging real-world scenario, we curate phone recognition datasets for Bukusu and Saamia, two varieties of the Luhya language cluster of western Kenya and eastern Uganda. We find that fine-tuning of Allosaurus, even with just 100 utterances, leads to significant improvements in phone error rates.
  arXiv  Detail & Related papers  (2021-04-04T15:07:55Z)
• Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music [1.2043574473965315]
  We propose a new method to identify the singer's name based on analysis of Vietnamese popular music. We employ the use of vocal segment detection and singing voice separation as the pre-processing steps. To verify the accuracy of our methods, we evaluate on a dataset of 300 Vietnamese songs from 18 famous singers.
  arXiv  Detail & Related papers  (2021-02-24T08:03:07Z)
• The Use of Voice Source Features for Sung Speech Recognition [24.129307615741695]
  We first use a parallel singing/speaking corpus to illustrate differences in sung vs spoken voicing characteristics. We then use this analysis to inform speech recognition experiments on the sung speech DSing corpus. Experiments are run with three standard (increasingly large) training sets, DSing1 (15.1 hours), DSing3 (44.7 hours) and DSing30 (149.1 hours)
  arXiv  Detail & Related papers  (2021-02-20T15:54:26Z)
• JukeBox: A Multilingual Singer Recognition Dataset [17.33151600403503]
  textitJukeBox is a speaker recognition dataset with multilingual singing voice audio annotated with singer identity, gender, and language labels. We use the current state-of-the-art methods to demonstrate the difficulty of performing speaker recognition on singing voice using models trained on spoken voice alone.
  arXiv  Detail & Related papers  (2020-08-08T12:22:51Z)
• DeepSinger: Singing Voice Synthesis with Data Mined From the Web [194.10598657846145]
  DeepSinger is a multi-lingual singing voice synthesis system built from scratch using singing training data mined from music websites. We evaluate DeepSinger on our mined singing dataset that consists of about 92 hours data from 89 singers on three languages.
  arXiv  Detail & Related papers  (2020-07-09T07:00:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.