An approach to optimize inference of the DIART speaker diarization pipeline
Not on the map. Why?
Abstract (arXiv)
Speaker diarization answers the question "who spoke when" for an audio file. In some diarization scenarios, low latency is required for transcription. Speaker diarization with low latency is referred to as online speaker diarization. The DIART pipeline is an online speaker diarization system. It consists of a segmentation and an embedding model. The embedding model has the largest share of the overall latency. The aim of this paper is to optimize the inference latency of the DIART pipeline. Different inference optimization methods such as knowledge distilation, pruning, quantization and layer fusion are applied to the embedding model of the pipeline. It turns out that knowledge distillation optimizes the latency, but has a negative effect on the accuracy. Quantization and layer fusion also have a positive influence on the latency without worsening the accuracy. Pruning, on the other hand, does not improve latency.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 5 Aug 2024.
Builds on
20 of 39 references.
References · 20
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
- 2014FitNets: Hints for Thin Deep Netscited by 1,619
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
- 2018Rethinking the Value of Network Pruningcited by 595
- 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
- 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
- 2015Quantized Convolutional Neural Networks for Mobile Devicescited by 212
- 2019pyannote.audio: neural building blocks for speaker diarizationcited by 175
- 2015Fixed Point Quantization of Deep Convolutional Networkscited by 141
- 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
- 2023ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensationcited by 78
8 more
- 2020Spot the conversation: speaker diarisation in the wildcited by 75
- 2022Knowledge Distillation via the Target-aware Transformercited by 70
- 2020Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard taskscited by 69
- 2020Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learningcited by 26
- 2021Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classificationcited by 14
- 2021Overlap-aware low-latency online speaker diarization based on end-to-end local segmentationcited by 14
- 2022DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Acceleratorscited by 2
- 2021Compact CNN Structure Learning by Knowledge Distillationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.