SOTAVerified

Speaker Diarization

Speaker Diarization is the task of segmenting and co-indexing audio recordings by speaker. The way the task is commonly defined, the goal is not to identify known speakers, but to co-index segments that are attributed to the same speaker; in other words, diarization implies finding speaker boundaries and grouping segments that belong to the same speaker, and, as a by-product, determining the number of distinct speakers. In combination with speech recognition, diarization enables speaker-attributed speech-to-text transcription.

Source: Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm

Papers

Showing 5160 of 328 papers

TitleStatusHype
End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label ClassificationCode1
Speaker Diarization with Region Proposal NetworkCode1
Phoneme Boundary Detection using Learnable Segmental FeaturesCode1
End-to-End Neural Speaker Diarization with Self-attentionCode1
AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker DetectionCode1
Speaker Diarization with LSTMCode1
Exploring Speaker Diarization with Mixture of Experts0
M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset0
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models0
SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition0
Show:102550
← PrevPage 6 of 33Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1COS+NJW-SC (Oracle SAD)DER(%)24.05Unverified
2EENDDER(%)23.07Unverified
3COS+AHC (Oracle SAD)DER(%)21.13Unverified
4SA-EEND (2-spk, no-adapt)DER(%)12.66Unverified
5EEND-OLADER(%)12.57Unverified
6SA-EEND (2-spk, adapted)DER(%)10.76Unverified
7TOLDDER(%)10.14Unverified
8COS+B-SC (Oracle SAD)DER(ig olp)8.78Unverified
9PLDA+AHC (Oracle SAD)DER(ig olp)8.39Unverified
10COS+NME-SC (Oracle SAD)DER(ig olp)7.29Unverified
#ModelMetricClaimedVerifiedStatus
1x-vector (PLDA + AHC)DER(%)8.39Unverified
2TitaNet-L (NME-SC)DER(%)6.73Unverified
3TitaNet-M (NME-SC)DER(%)6.47Unverified
4TitaNet-S (NME-SC)DER(%)6.37Unverified
5x-vector (MCGAN)DER(%)5.73Unverified
#ModelMetricClaimedVerifiedStatus
1ECAPA (SC)DER(%)2.36Unverified
2TitaNet-L (NME-SC)DER(%)2.03Unverified
3TitaNet-S (NME-SC)DER(%)2Unverified
4TitaNet-M (NME-SC)DER(%)1.99Unverified
#ModelMetricClaimedVerifiedStatus
1TitaNet-S (NME-SC)DER(%)2.22Unverified
2TitaNet-M (NME-SC)DER(%)1.79Unverified
3ECAPA (SC)DER(%)1.78Unverified
4TitaNet-L (NME-SC)DER(%)1.73Unverified
#ModelMetricClaimedVerifiedStatus
1x-vector (PLDA + AHC)DER(%)9.72Unverified
2TitaNet-L (NME-SC)DER(%)1.19Unverified
3TitaNet-M (NME-SC)DER(%)1.13Unverified
4TitaNet-S (NME-SC)DER(%)1.11Unverified
#ModelMetricClaimedVerifiedStatus
1Baseline (the best result in the literature as of Oct.2019)DER(%)11.2Unverified
2pyannote (MFCC)DER(%)10.5Unverified
3pyannote (waveform)DER(%)9.9Unverified
#ModelMetricClaimedVerifiedStatus
1BaselineDER(%)7.7Unverified
2pyannote (MFCC)DER(%)5.6Unverified
3pyannote (waveform)DER(%)4.9Unverified
#ModelMetricClaimedVerifiedStatus
1pyannote (MFCC)DER(%)6.3Unverified
2pyannote (waveform)DER(%)6Unverified
#ModelMetricClaimedVerifiedStatus
1d-vector + spectralDER(%)12.54Unverified
2titanet-sDER(%)1.11Unverified
#ModelMetricClaimedVerifiedStatus
1SONDDER(%)4.46Unverified
#ModelMetricClaimedVerifiedStatus
1UIS-RNN-SMLDER(%)27.3Unverified
#ModelMetricClaimedVerifiedStatus
1UIS-RNNV10.6Unverified