What tasks can Lyrics-Guided Singing Transcription · STARS help with?

MIDI / transcription; MIDI / JSON; Edit notes, instrumentation and performance details.; Supports inputs in formats such as mp3 / wav / flac / ogg / m4a / aac / aif / aiff / mp4 / mov / mkv; STARS Chinese; STARS Chinese-English

Lyrics-Guided Singing Transcription · STARS · TelkNet

MIDI / transcriptionGPU workload

Lyrics-Guided Singing Transcription · STARS

Q: Who is Lyrics-Guided Singing Transcription · STARS for?

MIDI / transcription Requires the vocal audio plus lyrics, phonemes and a phoneme-to-word map. Exports note MIDI together with phoneme, word and vocal-technique timing

Q: Which models and related terms are associated with Lyrics-Guided Singing Transcription · STARS?

STARS Chinese, STARS Chinese-English, STARS source (pinned), STARS weights (pinned), STARS paper, STARS paper, Table 2, STARS, Note transcription and lyric alignment · paper Table 2

Requires the vocal audio plus lyrics, phonemes and a phoneme-to-word map. Exports note MIDI together with phoneme, word and vocal-technique timing; it is not an audio-only route.

25 credits/useFile inputMax 100 MBEstimated 60-2400 seconds

Input

Supports inputs in formats such as mp3 / wav / flac / ogg / m4a / aac / aif / aiff / mp4 / mov / mkv

Supported formats

mp3wavflacoggm4aaacaifaiffmp4movmkv

Output

MIDI / JSON

Use case

Edit notes, instrumentation and performance details.

Models, parameters, and sources

STARS ChineseSTARS Chinese-EnglishSTARS source (pinned)STARS weights (pinned)STARS paperSTARS paper, Table 2STARSNote transcription and lyric alignment · paper Table 2Paper Table 2ROSVOTVOCANOSTARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation

STARS Chinese

STARS source (pinned)STARS weights (pinned)STARS paper

Enter a JSON array or whitespace-separated words. Contiguous Chinese text is split into characters.
Enter a JSON array or a space/comma-separated phoneme sequence using the selected STARS phone set.
Enter one zero-based word index per phoneme. The index count must equal the phoneme count.

STARS Chinese-English

STARS source (pinned)STARS weights (pinned)STARS paper

Enter a JSON array or whitespace-separated words. Contiguous Chinese text is split into characters.
Enter a JSON array or a space/comma-separated phoneme sequence using the selected STARS phone set.
Enter one zero-based word index per phoneme. The index count must equal the phoneme count.

Scores apply only to the cited dataset, metric and model version. Leading this table does not mean a current world record or a result from this service. Capabilities and tests can justify prioritizing models without comparable scores.

Public leaderboard: Lyrics-Guided Singing Transcription · STARS

Scores come from the cited public sources; blue rows are models available in this tool.

Lyrics-Guided Singing Transcription · STARS

STARS paper, Table 2

Values come from the linked public source. Row labels identify the test set or checkpoint; models without a matching result are omitted.

Rank	Test setting	Model	COnPOff F1 (%)	Detailed metrics
#1	Note transcription and lyric alignment · paper Table 2	STARSPaper Table 2	71.0Best	RPA (%)86.7Best
#2	Note transcription and lyric alignment · paper Table 2	ROSVOTPaper Table 2	70.2	RPA (%)83.8
#3	Note transcription and lyric alignment · paper Table 2	VOCANOPaper Table 2	50.2	RPA (%)76.6

Paper and benchmark notes

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation

ACL Findings - 2025

Paper Project demo

Official / repositories

STARS source (pinned)STARS weights (pinned)

Papers / technical notes

STARS paper

Parameter guide

Enter a JSON array or whitespace-separated words. Contiguous Chinese text is split into characters.
Enter a JSON array or a space/comma-separated phoneme sequence using the selected STARS phone set.
Enter one zero-based word index per phoneme. The index count must equal the phoneme count.

Workflow

1Upload vocals and supply lyrics, phonemes and phoneme-to-word indices.
2Generate MIDI and alignment annotations with STARS, then review note and lyric timing.

Before you submit

Enter a JSON array or whitespace-separated words. Contiguous Chinese text is split into characters.
Enter a JSON array or a space/comma-separated phoneme sequence using the selected STARS phone set.
Enter one zero-based word index per phoneme. The index count must equal the phoneme count.

Quick feedback

Include the tool name, steps and the problem in your feedback. Screenshots can help us locate it.