Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental component of modern diarization systems. Recently, some improvements over the standard TDNN architecture used for x-vectors have been proposed. The ECAPA-TDNN model, for instance, has shown impressive performance in the speaker verification domain, thanks to a carefully designed neural model.In this work, we extend, for the first time, the use of the ECAPA-TDNN model to speaker diarization. Moreover, we improved its robustness with a powerful augmentation scheme that concatenates several contaminated versions of the same signal within the same training batch. The ECAPA-TDNN model turned out to provide robust speaker embeddings under both close-talking and distant-talking conditions. Our results on the popular AMI meeting corpus show that our system significantly outperforms recently proposed approaches.

In this paper, we present a two-pass Information Bottleneck (IB) based system for speaker diarization which uses meetingspecific artificial neural network (ANN) based features. We first use IB based speaker diarization system to get the labelled speaker segments. These segments are re-segmented using Kullback-Leibler Hidden Markov Model (KL-HMM) based re-segmentation. The multi-layer ANN is then trained to discriminate these speakers using the re-segmented output labels and the spectral features. We then extract the bottleneck features from the trained ANN and perform principal component analysis (PCA) on these features. After performing PCA, these bottleneck features are used along with the different spectral features in the second pass using the same IB based system with KL-HMM re-segmentation. Our experiments on NIST RT and AMI datasets show that the proposed system performs better than the baseline IB system in terms of speaker error rate (SER) with a best case relative improvement of 28.6% amongst AMI datasets and 27.1% on NIST RT04eval dataset.

No abstract

The two-pass information bottleneck (TPIB) based speaker diarization system operates independently on different conversational recordings. TPIB system does not consider previously learned speaker discriminative information while diarizing new conversations. Hence, the real time factor (RTF) of TPIB system is high owing to the training time required for the artificial neural network (ANN). This paper attempts to improve the RTF of the TPIB system using an incremental transfer learning approach where the parameters learned by the ANN from other conversations are updated using current conversation rather than learning parameters from scratch. This reduces the RTF significantly. The effectiveness of the proposed approach compared to the baseline IB and the TPIB systems is demonstrated on standard NIST and AMI conversational meeting datasets. With a minor degradation in performance, the proposed system shows a significant improvement of 33.07% and 24.45% in RTF with respect to TPIB system on the NIST RT-04Eval and AMI-1 datasets, respectively.

An approach to diarize taniavartanam segments of a Carnatic music concert is proposed in this paper. Information bottleneck (IB) based approach used for speaker diarization is applied for this task. IB system initializes the segments to be clustered uniformly with fixed duration. The issue with diarization of percussion instruments in taniavartanam is that the stroke rate varies highly across the segments. It can double or even quadruple within a short duration, thus leading to variable information rate in different segments. To address this issue, the IB system is modified to use the stroke rate information to divide the audio into segments of varying durations. These varying duration segments are then clustered using the IB approach which is then followed by Kullback-Leibler hidden Markov model (KL-HMM) based realignment of the instrument boundaries. Performance of the conventional IB system and the proposed system is evaluated on standard Carnatic music dataset. The proposed technique shows a best case absolute improvement of 8.2% over the conventional IB based system in terms of diarization error rate.