Causal-anticausal consistency co-training recovers about 70% of the boundary-tightening effect possible with ideal tight labels in speaker diarization.
Investigating the effects of large-scale pseudo-stereo data and different speech foundation model on dialogue generative spoken language model
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2representative citing papers
ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.
citing papers explorer
-
Tight Boundary Prediction in Speaker Diarization Using Causal-Anticausal Consistency
Causal-anticausal consistency co-training recovers about 70% of the boundary-tightening effect possible with ideal tight labels in speaker diarization.
-
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and reports better speed and quality than autoregressive baselines.