DeepAI
Log In Sign Up

Exploring Tradeoffs in Models for Low-latency Speech Enhancement

11/16/2018
by   Kevin Wilson, et al.
0

We explore a variety of neural networks configurations for one- and two-channel spectrogram-mask-based speech enhancement. Our best model improves on previous state-of-the-art performance on the CHiME2 speech enhancement task by 0.4 decibels in signal-to-distortion ratio (SDR). We examine trade-offs such as non-causal look-ahead, computation, and parameter count versus enhancement performance and find that zero-look-ahead models can achieve, on average, within 0.03 dB SDR of our best bidirectional model. Further, we find that 200 milliseconds of look-ahead is sufficient to achieve equivalent performance to our best bidirectional model.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/03/2022

Iterative autoregression: a novel trick to improve your low-latency speech enhancement model

Streaming models are an essential component of real-time speech enhancem...
08/27/2021

Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement

As the cornerstone of other important technologies, such as speech recog...
03/27/2021

On TasNet for Low-Latency Single-Speaker Speech Enhancement

In recent years, speech processing algorithms have seen tremendous progr...
05/06/2021

Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU

Single channel speech enhancement is a challenging task in speech commun...
12/11/2018

R3-DLA (Reduce, Reuse, Recycle): A More Efficient Approach to Decoupled Look-Ahead Architectures

Modern societies have developed insatiable demands for more computation ...