2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDSPE-41.2
Paper Title A HYBRID CNN-BILSTM VOICE ACTIVITY DETECTOR
Authors Nicholas Wilkinson, Thomas Niesler, Stellenbosch University, South Africa
SessionSPE-41: Voice Activity and Disfluency Detection
LocationGather.Town
Session Time:Thursday, 10 June, 15:30 - 16:15
Presentation Time:Thursday, 10 June, 15:30 - 16:15
Presentation Poster
Topic Speech Processing: [SPE-VAD] Voice Activity Detection and End-pointing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract This paper presents a new hybrid architecture for voice activity detection (VAD) incorporating both convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) layers trained in an end-to-end manner. In addition, we focus specifically on optimising the computational efficiency of our architecture in order to deliver robust performance in difficult in-the-wild noise conditions in a severely under-resourced setting. Nested k-fold cross-validation was used to explore the hyperparameter space, and the trade-off between optimal parameters and model size is discussed. The performance effect of a BiLSTM layer compared to a unidirectional LSTM layer was also considered. We compare our systems with three established baselines on the AVA-Speech dataset. We find that significantly smaller models with near optimal parameters perform on par with larger models trained with optimal parameters. BiLSTM layers were shown to improve accuracy over unidirectional layers by ≈2% absolute on average. With an area under the curve (AUC) of 0.951, our system outperforms all baselines, including a much larger ResNet system, particularly in difficult noise conditions.