no code implementations • 26 Feb 2024 • Tassadaq Hussain, Kia Dashtipour, Yu Tsao, Amir Hussain
By integrating emotional features, the proposed system achieves significant improvements in both objective and subjective assessments of speech quality and intelligibility, especially in challenging noise environments.
no code implementations • 31 Oct 2022 • I-Chun Chern, Kuo-Hsuan Hung, Yi-Ting Chen, Tassadaq Hussain, Mandar Gogate, Amir Hussain, Yu Tsao, Jen-Cheng Hou
In summary, our results confirm the effectiveness of our proposed model for the AVSS task with proper fine-tuning strategies, demonstrating that multi-modal self-supervised embeddings obtained from AV-HuBERT can be generalized to audio-visual regression tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • 11 Feb 2022 • Tassadaq Hussain, Muhammad Diyan, Mandar Gogate, Kia Dashtipour, Ahsan Adeel, Yu Tsao, Amir Hussain
Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are often trained to minimise the feature distance between noise-free speech and enhanced speech signals.
no code implementations • 8 Feb 2022 • Tassadaq Hussain, Muhammad Diyan, Mandar Gogate, Kia Dashtipour, Ahsan Adeel, Yu Tsao, Amir Hussain
Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are generally trained to minimise the distance between clean and enhanced speech features.
no code implementations • 24 Jan 2022 • Tassadaq Hussain, Wei-Chien Wang, Mandar Gogate, Kia Dashtipour, Yu Tsao, Xugang Lu, Adeel Ahsan, Amir Hussain
To address this problem, we propose to integrate a novel temporal attentive-pooling (TAP) mechanism into a conventional convolutional recurrent neural network, termed as TAP-CRNN.
1 code implementation • 18 Nov 2021 • Tassadaq Hussain, Mandar Gogate, Kia Dashtipour, Amir Hussain
To the best of our knowledge, this is the first work that exploits the integration of AV modalities with an I-O based loss function for SE.