ECAPA-TDNN Embeddings for Speaker Diarization

Abstract

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.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Res2Net: A New Multi-scale Backbone Architecture
• VoxCeleb2: Deep Speaker Recognition
• Squeeze-and-Excitation Networks
• VoxCeleb: a large-scale speaker identification dataset
• ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
• SpeechBrain: A General-Purpose Speech Toolkit
• BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
• VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
• Augment your batch: better training with larger batches
• Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization

Cited by in corpus (11)

• SpeechBrain: A General-Purpose Speech Toolkit
• Modulation spectral features for speech emotion recognition using deep neural networks
• Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors
• Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio
• Analysis of constant-Q filterbank based representations for speech emotion recognition
• Implicit Self-supervised Language Representation for Spoken Language Diarization
• North America Bixby Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2021
• Residual Information in Deep Speaker Embedding Architectures
• Self-Tuning Spectral Clustering for Speaker Diarization
• Long-Term Conversation Analysis: Privacy-Utility Trade-off under Noise and Reverberation
• An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS