Fully Supervised Speaker Diarization
This addresses speaker diarization for speech processing applications, offering an online decoding capability, but it is incremental as it builds on existing embedding and clustering techniques.
The paper tackles speaker diarization by proposing a fully supervised approach using unbounded interleaved-state RNNs with a distance-dependent Chinese restaurant process, achieving a 7.6% diarization error rate on NIST SRE 2000 CALLHOME, outperforming spectral clustering methods.
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input utterances, each individual speaker is modeled by a parameter-sharing RNN, while the RNN states for different speakers interleave in the time domain. This RNN is naturally integrated with a distance-dependent Chinese restaurant process (ddCRP) to accommodate an unknown number of speakers. Our system is fully supervised and is able to learn from examples where time-stamped speaker labels are annotated. We achieved a 7.6% diarization error rate on NIST SRE 2000 CALLHOME, which is better than the state-of-the-art method using spectral clustering. Moreover, our method decodes in an online fashion while most state-of-the-art systems rely on offline clustering.