RECORD
Array Configuration-Agnostic Personal Voice Activity Detection Based on Spatial Coherence
Audio and Speech Processing · Submitted 18 Apr 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimental results have demonstrated the superior performance achieved by the proposed ARCA-PVAD system over a baseline in terms of the area under receiver operating characteristic curve and equal error rate.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Personal voice activity detection has received increased attention due to the growing popularity of personal mobile devices and smart speakers. PVAD is often an integral element to speech enhancement and recognition for these applications in which lightweight signal processing is only enabled for the target user. However, in real-world scenarios, the detection performance may degrade because of competing speakers, background noise, and reverberation. To address this problem, we proposed to use equivalent rectangular bandwidth ERB-scaled spatial coherence as the input feature to train an array configuration-agnostic PVAD network. Whereas the network model requires only 112k parameters, it exhibits excellent detection performance and robustness in adverse acoustic conditions. Notably, the proposed ARCA-PVAD system is scalable to array configurations. Experimental results have demonstrated the superior performance achieved by the proposed ARCA-PVAD system over a baseline in terms of the area under receiver operating characteristic curve and equal error rate.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Personal voice activity detection has received increased attention due to the growing popularity of personal mobile devices and smart speakers. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | PVAD is often an integral element to speech enhancement and recognition for these applications in which lightweight signal processing is only enabled for the target user. | background 1.00 | 0.05 | 0.03 | asserted 0.98 |
| s2 | However, in real-world scenarios, the detection performance may degrade because of competing speakers, background noise, and reverberation. | background 0.79 | 0.07 | 0.02 | hedged possibility 1.00 |
| s3 | To address this problem, we proposed to use equivalent rectangular bandwidth ERB-scaled spatial coherence as the input feature to train an array configuration-agnostic PVAD network. | method 0.76 | 0.93 | 0.12 | asserted 0.85 |
| s4 | Whereas the network model requires only 112k parameters, it exhibits excellent detection performance and robustness in adverse acoustic conditions. | result 0.94 | 0.90 | 0.36 | asserted 1.00 |
| s5 | Notably, the proposed ARCA-PVAD system is scalable to array configurations. | contribution 0.36 | 0.70 | 0.16 | asserted 1.00 |
| s6 | Experimental results have demonstrated the superior performance achieved by the proposed ARCA-PVAD system over a baseline in terms of the area under receiver operating characteristic curve and equal error rate. | result 1.00 | 0.95 | 0.57 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Personal voice activity detection has received increased attention due to the growing popularity of personal mobile devices and smart speakers. PVAD is often an integral element to speech enhancement and recognition for these applications in which lightweight signal processing is only enabled for the target user. However, in real-world scenarios, the detection performance may degrade because of competing speakers, background noise, and reverberation. To address this problem, we proposed to use equivalent rectangular bandwidth ERB-scaled spatial coherence as the input feature to train an array configuration-agnostic PVAD network. Whereas the network model requires only 112k parameters, it exhibits excellent detection performance and robustness in adverse acoustic conditions. Notably, the proposed ARCA-PVAD system is scalable to array configurations. Experimental results have demonstrated the superior performance achieved by the proposed ARCA-PVAD system over a baseline in terms of the area under receiver operating characteristic curve and equal error rate.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.