Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks
| Autor: | Federico Landini, Mireia Diez, Lukas Burget, Ján Profant |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Protocol (science)
FOS: Computer and information sciences Sequence Sound (cs.SD) Point (typography) Computer science Speech recognition 010102 general mathematics Bayesian probability 02 engineering and technology 01 natural sciences Computer Science - Sound Theoretical Computer Science Human-Computer Interaction Speaker diarisation Audio and Speech Processing (eess.AS) Cepstrum 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 0101 mathematics Cluster analysis Hidden Markov model Software Electrical Engineering and Systems Science - Audio and Speech Processing |
| Popis: | The recently proposed VBx diarization method uses a Bayesian hidden Markov model to find speaker clusters in a sequence of x-vectors. In this work we perform an extensive comparison of performance of the VBx diarization with other approaches in the literature and we show that VBx achieves superior performance on three of the most popular datasets for evaluating diarization: CALLHOME, AMI and DIHARDII datasets. Further, we present for the first time the derivation and update formulae for the VBx model, focusing on the efficiency and simplicity of this model as compared to the previous and more complex BHMM model working on frame-by-frame standard Cepstral features. Together with this publication, we release the recipe for training the x-vector extractors used in our experiments on both wide and narrowband data, and the VBx recipes that attain state-of-the-art performance on all three datasets. Besides, we point out the lack of a standardized evaluation protocol for AMI dataset and we propose a new protocol for both Beamformed and Mix-Headset audios based on the official AMI partitions and transcriptions. Submitted to Computer Speech and Language, Special Issue on Separation, Recognition, and Diarization of Conversational Speech |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|