Recurrent Neural Networks and Acoustic Features for Frame-Level Signal-to-Noise Ratio Estimation
Recurrent Neural Networks and Acoustic Features for Frame-Level Signal-to-Noise Ratio Estimation
复制标题
用于帧级信噪比估计的循环神经网络和声学特征
DOI：
10.1109/taslp.2021.3107617
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Guanglai Gao
中科院分区：
文献类型：
--
作者：
Hao Li;DeLiang Wang;Xueliang Zhang;Guanglai Gao
It is important to know the presence and the relative level of background noise for many speech processing tasks. Frame-level signal-to-noise ratio (SNR) provides a measure of instantaneous noise level of a noisy signal, and its estimation has been researched for decades. This problem can be approached from a supervised learning perspective by predicting SNR from features of noisy speech. In this study, we introduce a deep learning algorithm for frame-level SNR estimation. The proposed algorithm employs recurrent neural networks (RNNs) with long short-term memory (LSTM) to leverage contextual information. We also systematically examine a range of acoustic features and investigate feature combinations using Group Lasso and sequential floating forward selection (SFFS). The proposed algorithm naturally leads to an utterance-level SNR estimator. Systematical evaluations show that the proposed algorithm provides an accurate estimate of frame-level SNR, as well as utterance-level SNR, under different noise conditions, outperforming other estimators.
登录
查看更多内容
DOI：
10.1109/89.279283
发表时间：
1994-04-01
期刊：
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING
影响因子：
--
作者：
Cappe, Olivier
通讯作者：
Cappe, Olivier
DOI：
10.1109/tasl.2012.2205242
发表时间：
2012-11
期刊：
IEEE Transactions on Audio, Speech, and Language Processing
影响因子：
--
作者：
A. Narayanan;Deliang Wang
通讯作者：
A. Narayanan;Deliang Wang
影响因子：
4.3
作者：
Dirk Van Compernolle
通讯作者：
Dirk Van Compernolle
DOI：
10.1121/1.3699200
发表时间：
2012-05
期刊：
The Journal of the Acoustical Society of America
影响因子：
--
作者：
M. R. Schädler;B. Meyer;B. Kollmeier
通讯作者：
M. R. Schädler;B. Meyer;B. Kollmeier
DOI：
10.21437/interspeech.2020-2475
发表时间：
2020-10
期刊：
IEEE Transactions on Audio, Speech, and Language Processing
影响因子：
--
作者：
Hao Li;Deliang Wang;Xueliang Zhang;Guanglai Gao
通讯作者：
Hao Li;Deliang Wang;Xueliang Zhang;Guanglai Gao