# Singing

Source: [Singing](<https://www.sota2.com/research/dataset/singing>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Benchmarks

Page 1 of 1. This is an index page, not the full collection.

- [Audio Synthesis on Singing Voice MUSHRA (evaluation)](<https://www.sota2.com/research/sota/audio-synthesis-on-singing-voice-mushra-evaluation.md>): Audio Synthesis; Singing Voice MUSHRA (evaluation).

- [Audio Synthesis on Singing Voice Industrial setting](<https://www.sota2.com/research/sota/audio-synthesis-on-singing-voice-industrial-setting.md>): Audio Synthesis; Singing Voice Industrial setting.

- [Audio Synthesis on Singing Voice Academic setting](<https://www.sota2.com/research/sota/audio-synthesis-on-singing-voice-academic-setting.md>): Audio Synthesis; Singing Voice Academic setting.

- [Fundamental Frequency Estimation on Speech, Singing Voice, and Music Clean](<https://www.sota2.com/research/sota/fundamental-frequency-estimation-on-speech-singing-voice-and-music-clean.md>): Fundamental Frequency Estimation; Speech, Singing Voice, and Music Clean.

- [Singing Voice Synthesis on Singing Voice Industrial Setting](<https://www.sota2.com/research/sota/singing-voice-synthesis-on-singing-voice-industrial-setting.md>): Singing Voice Synthesis; Singing Voice Industrial Setting.

- [Singing Voice Synthesis on Singing Voice (Academic Setting)](<https://www.sota2.com/research/sota/singing-voice-synthesis-on-singing-voice-academic-setting.md>): Singing Voice Synthesis; Singing Voice (Academic Setting).

- [Speech Activity Detection on MoisesDB (singing-only)](<https://www.sota2.com/research/sota/speech-activity-detection-on-moisesdb-singing-only.md>): Speech Activity Detection; MoisesDB (singing-only).

- [Zero-shot Text-to-Speech on Singing Voice](<https://www.sota2.com/research/sota/zero-shot-text-to-speech-on-singing-voice.md>): Zero-shot Text-to-Speech; Singing Voice.

- [Audio-Visual Deepfake Detection on SHDF singing (test)](<https://www.sota2.com/research/sota/audio-visual-deepfake-detection-on-shdf-singing-test.md>): Audio-Visual Deepfake Detection; SHDF singing (test).

- [Speech-to-Singing Style Transfer Zero-shot (test)](<https://www.sota2.com/research/sota/speech-to-singing-style-transfer-zero-shot-test.md>): Speech-to-Singing Style Transfer; Speech-to-Singing Style Transfer Zero-shot (test).

- [Multi-level Singing Style Control on Singing dataset Parallel (test)](<https://www.sota2.com/research/sota/multi-level-singing-style-control-on-singing-dataset-parallel-test.md>): Multi-level Singing Style Control; Singing dataset Parallel (test).

- [Singing Voice Audio Reconstruction on Singing Voice Audio Dataset (test)](<https://www.sota2.com/research/sota/singing-voice-audio-reconstruction-on-singing-voice-audio-dataset-test.md>): Singing Voice Audio Reconstruction; Singing Voice Audio Dataset (test).

- [Multi-Singer Singing Voice Synthesis on Multi-Singer Singing (test)](<https://www.sota2.com/research/sota/multi-singer-singing-voice-synthesis-on-multi-singer-singing-test.md>): Multi-Singer Singing Voice Synthesis; Multi-Singer Singing (test).

- [Singing Lyrics Recognition on Singing lyrics (test)](<https://www.sota2.com/research/sota/singing-lyrics-recognition-on-singing-lyrics-test.md>): Singing Lyrics Recognition; Singing lyrics (test).

- [Multi-level Singing Style Control on Singing dataset Non-Parallel (test)](<https://www.sota2.com/research/sota/multi-level-singing-style-control-on-singing-dataset-non-parallel-test.md>): Multi-level Singing Style Control; Singing dataset Non-Parallel (test).

- [Singing Voice Synthesis on Singing (evaluation set)](<https://www.sota2.com/research/sota/singing-voice-synthesis-on-singing-evaluation-set.md>): Singing Voice Synthesis; Singing (evaluation set).

- [Singing Lyric Editing on Singing Voice Editing](<https://www.sota2.com/research/sota/singing-lyric-editing-on-singing-voice-editing.md>): Singing Lyric Editing; Singing Voice Editing.

- [Singing Voice Editing (Structural Editing) on Mandarin singing vocals (DiffRhythm)](<https://www.sota2.com/research/sota/singing-voice-editing-structural-editing-on-mandarin-singing-vocals-diffrhythm.md>): Singing Voice Editing (Structural Editing); Mandarin singing vocals (DiffRhythm).

- [Singing Voice Editing (Lyrics Editing) on DiffRhythm Mandarin singing vocals](<https://www.sota2.com/research/sota/singing-voice-editing-lyrics-editing-on-diffrhythm-mandarin-singing-vocals.md>): Singing Voice Editing (Lyrics Editing); DiffRhythm Mandarin singing vocals.

- [Singing Voice Synthesis on Korean singing voice dataset (test)](<https://www.sota2.com/research/sota/singing-voice-synthesis-on-korean-singing-voice-dataset-test.md>): Singing Voice Synthesis; Korean singing voice dataset (test).

- [Robotic Singing Performance Generation on Collected singing vocal clips (test)](<https://www.sota2.com/research/sota/robotic-singing-performance-generation-on-collected-singing-vocal-clips-test.md>): Robotic Singing Performance Generation; Collected singing vocal clips (test).

- [Music Generation on Song Describer Dataset no-singing](<https://www.sota2.com/research/sota/music-generation-on-song-describer-dataset-no-singing.md>): Music Generation; Song Describer Dataset no-singing.

- [Music Generation on Song Describer Dataset no-singing (test)](<https://www.sota2.com/research/sota/music-generation-on-song-describer-dataset-no-singing-test.md>): Music Generation; Song Describer Dataset no-singing (test).

- [Singing Voice Editing on Singing Voice Editing Del scenario](<https://www.sota2.com/research/sota/singing-voice-editing-on-singing-voice-editing-del-scenario.md>): Singing Voice Editing; Singing Voice Editing Del scenario.

- [Singing Voice Editing on Singing Voice Editing Ins scenario](<https://www.sota2.com/research/sota/singing-voice-editing-on-singing-voice-editing-ins-scenario.md>): Singing Voice Editing; Singing Voice Editing Ins scenario.

- [Singing Voice Editing on Singing Voice Editing Rep-P scenario](<https://www.sota2.com/research/sota/singing-voice-editing-on-singing-voice-editing-rep-p-scenario.md>): Singing Voice Editing; Singing Voice Editing Rep-P scenario.

- [Singing Voice Generation on Singing (test)](<https://www.sota2.com/research/sota/singing-voice-generation-on-singing-test.md>): Singing Voice Generation; Singing (test).

- [Automatic Pitch Correction on Korean singing recordings MOS (test)](<https://www.sota2.com/research/sota/automatic-pitch-correction-on-korean-singing-recordings-mos-test.md>): Automatic Pitch Correction; Korean singing recordings MOS (test).

- [Singing Voice Synthesis on Mandarin singing vocals (DiffRhythm)](<https://www.sota2.com/research/sota/singing-voice-synthesis-on-mandarin-singing-vocals-diffrhythm.md>): Singing Voice Synthesis; Mandarin singing vocals (DiffRhythm).

- [Song Aesthetics Evaluation on internal dataset Singing](<https://www.sota2.com/research/sota/song-aesthetics-evaluation-on-internal-dataset-singing.md>): Song Aesthetics Evaluation; internal dataset Singing.

- [Music Generation on Song Describer Dataset no-singing 2m](<https://www.sota2.com/research/sota/music-generation-on-song-describer-dataset-no-singing-2m.md>): Music Generation; Song Describer Dataset no-singing 2m.

- [Note Transcription and Alignment on Multilingual singing dataset Chinese and English (test)](<https://www.sota2.com/research/sota/note-transcription-and-alignment-on-multilingual-singing-dataset-chinese-and-english-test.md>): Note Transcription and Alignment; Multilingual singing dataset Chinese and English (test).

- [Singing Voice Editing on Singing Voice Editing Mix scenario](<https://www.sota2.com/research/sota/singing-voice-editing-on-singing-voice-editing-mix-scenario.md>): Singing Voice Editing; Singing Voice Editing Mix scenario.

- [Singing Voice Editing on Singing Voice Editing Rep-SM scenario](<https://www.sota2.com/research/sota/singing-voice-editing-on-singing-voice-editing-rep-sm-scenario.md>): Singing Voice Editing; Singing Voice Editing Rep-SM scenario.

- [Singing Voice Editing on Singing Voice Editing Rep-S scenario](<https://www.sota2.com/research/sota/singing-voice-editing-on-singing-voice-editing-rep-s-scenario.md>): Singing Voice Editing; Singing Voice Editing Rep-S scenario.

- [Creativity Evaluation on Singing in Shower Specific prompt](<https://www.sota2.com/research/sota/creativity-evaluation-on-singing-in-shower-specific-prompt.md>): Creativity Evaluation; Singing in Shower Specific prompt.

- [Idea Generation on Singing in Shower](<https://www.sota2.com/research/sota/idea-generation-on-singing-in-shower.md>): Idea Generation; Singing in Shower.

- [Vocal Event Detection on WESR-Bench Singing 1.0](<https://www.sota2.com/research/sota/vocal-event-detection-on-wesr-bench-singing-1-0.md>): Vocal Event Detection; WESR-Bench Singing 1.0.

- [Music Generation on Song Describer Dataset no-singing subset 4m 45s](<https://www.sota2.com/research/sota/music-generation-on-song-describer-dataset-no-singing-subset-4m-45s.md>): Music Generation; Song Describer Dataset no-singing subset 4m 45s.

- [Singing Voice Generation on Bark Singing Voices official suno-ai implementation (test)](<https://www.sota2.com/research/sota/singing-voice-generation-on-bark-singing-voices-official-suno-ai-implementation-test.md>): Singing Voice Generation; Bark Singing Voices official suno-ai implementation (test).

- [Singing Voice Editing on In-the-wild singing data Singing Voice Editing (test)](<https://www.sota2.com/research/sota/singing-voice-editing-on-in-the-wild-singing-data-singing-voice-editing-test.md>): Singing Voice Editing; In-the-wild singing data Singing Voice Editing (test).