A time-frequency attention module for neural speech enhancement

Q Zhang, X Qian, Z Ni, A Nicolson… - … on Audio, Speech …, 2022 - ieeexplore.ieee.org
Speech enhancement plays an essential role in a wide range of speech processing
applications. Recent studies on speech enhancement tend to investigate how to effectively …

[HTML][HTML] Wiener filter and deep neural networks: A well-balanced pair for speech enhancement

D Ribas, A Miguel, A Ortega, E Lleida - Applied Sciences, 2022 - mdpi.com
This paper proposes a Deep Learning (DL) based Wiener filter estimator for speech
enhancement in the framework of the classical spectral-domain speech estimator algorithm …

[PDF][PDF] Data augmentation for children ASR and child-adult speaker classification using voice conversion methods

Z Shuyang, M Singh, A Woubie, R Karhila - Proc. Interspeech, 2023 - isca-archive.org
Many young children prefer speech based interfaces over text, as they are relatively slow
and error-prone with text input. However, children ASR can be challenging due to the lack of …

On supervised LPC estimation training targets for augmented Kalman filter-based speech enhancement

SK Roy, A Nicolson, KK Paliwal - Speech Communication, 2022 - Elsevier
The performance of speech coding, speech recognition, and speech enhancement systems
that rely on the augmented Kalman filter (AKF) largely depend upon the accuracy of clean …

Multi-target ensemble learning based speech enhancement with temporal-spectral structured target

W Wang, W Guo, H Liu, J Yang, S Liu - Applied Acoustics, 2023 - Elsevier
Recently, deep neural network (DNN)-based speech enhancement has shown considerable
success, and map**-based and masking-based are the two most commonly used …

[PDF][PDF] iDeepMMSE: An improved deep learning approach to MMSE speech and noise power spectrum estimation for speech enhancement.

M Kim, H Song, S Cheong, JW Shin - INTERSPEECH, 2022 - researchgate.net
Deep learning approaches have been successfully applied to single channel speech
enhancement exhibiting significant performance improvement. Recently, approaches …

Deep Neural Network-based Mixed Speech Recognition Technology for Chinese and English

L Han - ACM Transactions on Asian and Low-Resource …, 2023 - dl.acm.org
In the field of human-computer interaction, the current more advanced speech recognition
systems are all single speech recognition, and it is urgent to adopt new in-depth learning …

Deep Learning for Minimum Mean-Square Error and Missing Data Approaches to Robust Speech Processing

AM Nicolson - 2020 - research-repository.griffith.edu.au
Speech corrupted by background noise (or noisy speech) can cause misinterpretation and
fatigue during phone and conference calls, and for hearing aid users. Noisy speech can also …