DeepAI AI Chat
Log In Sign Up

Precision Scaling of Neural Networks for Efficient Audio Processing

by   Jong Hwan Ko, et al.
Georgia Institute of Technology
University of Washington

While deep neural networks have shown powerful performance in many audio applications, their large computation and memory demand has been a challenge for real-time processing. In this paper, we study the impact of scaling the precision of neural networks on the performance of two common audio processing tasks, namely, voice-activity detection and single-channel speech enhancement. We determine the optimal pair of weight/neuron bit precision by exploring its impact on both the performance and processing time. Through experiments conducted with real user data, we demonstrate that deep neural networks that use lower bit precision significantly reduce the processing time (up to 30x). However, their performance impact is low (< 3.14 classification tasks such as those present in voice activity detection.


page 1

page 2

page 3

page 4


Inference skipping for more efficient real-time speech enhancement with parallel RNNs

Deep neural network (DNN) based speech enhancement models have attracted...

The Hidden Power of Pure 16-bit Floating-Point Neural Networks

Lowering the precision of neural networks from the prevalent 32-bit prec...

Deep Neural Network Voice Activity Detector for Downsampled Audio Data: An Experiment Report

Sociometric badges are an emerging technology for study how teams intera...

Resource-Efficient Speech Mask Estimation for Multi-Channel Speech Enhancement

While machine learning techniques are traditionally resource intensive, ...

BC-VAD: A Robust Bone Conduction Voice Activity Detection

Voice Activity Detection (VAD) is a fundamental module in many audio app...

Deep Voice: Real-time Neural Text-to-Speech

We present Deep Voice, a production-quality text-to-speech system constr...

Voice Activity Detection for Transient Noisy Environment Based on Diffusion Nets

We address voice activity detection in acoustic environments of transien...