REVIEW 4 cited by
Neural Speaker Diarization with Speaker-Wise Chain Rule
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Speaker diarization is an essential step for processing multi-speaker audio. Although an end-to-end neural diarization (EEND) method achieved state-of-the-art performance, it is limited to a fixed number of speakers. In this paper, we solve this fixed number of speaker issue by a novel speaker-wise conditional inference method based on the probabilistic chain rule. In the proposed method, each speaker's speech activity is regarded as a single random variable, and is estimated sequentially conditioned on previously estimated other speakers' speech activities. Similar to other sequence-to-sequence models, the proposed method produces a variable number of speakers with a stop sequence condition. We evaluated the proposed method on multi-speaker audio recordings of a variable number of speakers. Experimental results show that the proposed method can correctly produce diarization results with a variable number of speakers and outperforms the state-of-the-art end-to-end speaker diarization methods in terms of diarization error rate.
Forward citations
Cited by 4 Pith papers
-
Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering
A streaming Sortformer with an arrival-ordered speaker cache achieves lower diarization error than prior online systems on DIHARD III and CALLHOME, even at 0.32 second latency.
-
Multi-Stage Speaker Diarization for Noisy Classrooms
A hybrid VAD that merges frame-level VAD with Whisper timestamps, plus denoising as training augmentation, reduces diarization error to 17% for teacher-student speech in noisy classrooms.
-
Music Tagging with Classifier Group Chains
A music tagger that predicts genre, instrument, and mood/theme groups in sequence, conditioning each group on earlier predictions, gives modest AUC gains over independent tag decoding.
-
Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm
Graph attention refinement plus overlapping label propagation yields a reported 15.94% DER on DIHARD-III without oracle VAD, though internal configuration inconsistencies and missing error bars make the SOTA claim pro...
Discussion (0). Continue with ORCID to comment.