Speaker Diarization With LSTM

Abstract

For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications. However, mirroring the rise of deep learning in various domains, neural network based audio embeddings, also known as d-vectors, have consistently demonstrated superior speaker verification performance. In this paper, we build on the success of d-vector based speaker verification systems to develop a new d-vector based approach to speaker diarization. Specifically, we combine LSTM-based d-vector audio embeddings with recent work in non-parametric clustering to obtain a state-of-the-art speaker diarization system. Our system is evaluated on three standard public datasets, suggesting that d-vector based diarization systems offer significant advantages over traditional i-vector based systems. We achieved a 12.0% diarization error rate on NIST SRE 2000 CALLHOME, while our model is trained with out-of-domain data from voice search logs.

Stats

• citations213
• S2 citations—
• github stars0
• HF likes0
• heat score17.48
• arxiv keywang2017speaker

Related papers

• Speaker Diarization Using Deep Recurrent Convolutional Neural Networks For Speaker Embeddings (2017)9.41
• Combination Of Deep Speaker Embeddings For Diarisation (2020)8.60
• LSTM Based Similarity Measurement With Spectral Clustering For Speaker Diarization (2019)13.79
• Speaker Diarization Using Two-pass Leave-one-out Gaussian PLDA Clustering Of DNN Embeddings (2021)2.26
• Leveraging Speaker Embeddings In End-to-end Neural Diarization For Two-speaker Scenarios (2024)0.00
• Speaker Diarisation Using 2D Self-attentive Combination Of Embeddings (2019)9.92
• Fully Supervised Speaker Diarization (2018)15.80
• Speaker Diarization With Lexical Information (2018)9.76