36 citations · 195 across the 52 of their papers we have counts for
15 papers · 1 filter
Analysis of Speech Separation Performance Degradation on Emotional Speech Mixtures
Jia Qi Yip, Dianwen Ng, Bin Ma +1
Despite recent strides made in Speech Separation, most models are trained on datasets with neutral emotions. Emotional speech has been known to degrade performance of models in a v…
A Neural State-Space Model Approach to Efficient Speech Separation
Chen Chen, Chao-Han Huck Yang, Kai Li +3
In this work, we introduce S4M, a new efficient speech separation framework based on neural state-space models (SSM). Motivated by linear time-invariant systems for sequence modeli…
Study of GANs for Noisy Speech Simulation from Clean Speech
Leander Melroy Maben, Zixun Guo, Chen Chen +2
The performance of speech processing models trained on clean speech drops significantly in noisy conditions. Training with noisy datasets alleviates the problem, but procuring such…
ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Jia Qi Yip, Tuan Truong, Dianwen Ng +7
In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetri…
Metric-oriented Speech Enhancement using Diffusion Probabilistic Model
Chen Chen, Yuchen Hu, Weiwei Weng +1
Deep neural network based speech enhancement technique focuses on learning a noisy-to-clean transformation supervised by paired training data. However, the task-specific evaluation…
Unsupervised Noise adaptation using Data Simulation
Chen Chen, Yuchen Hu, Heqing Zou +2
Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformati…
I2CR: Improving Noise Robustness on Keyword Spotting Using Inter-Intra Contrastive Regularization
Dianwen Ng, Jia Qi Yip, Tanmay Surana +6
Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing the deterioration of the quality of feature embeddin…
Continual Learning For On-Device Environmental Sound Classification
Yang Xiao, Xubo Liu, James King +4
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation re…
Language-Based Audio Retrieval with Converging Tied Layers and Contrastive Loss
Andrew Koh, Eng Siong Chng
In this paper, we tackle the new Language-Based Audio Retrieval task proposed in DCASE 2022. Firstly, we introduce a simple, scalable architecture which ties both the audio and tex…
Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
Chen Chen, Nana Hou, Yuchen Hu +3
Automated Audio captioning (AAC) is a cross-modal task that generates natural language to describe the content of input audio. Most prior works usually extract single-modality acou…
Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information
Heqing Zou, Yuke Si, Chen Chen +2
Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-d…
Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data
Chen Chen, Nana Hou, Yuchen Hu +2
Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in…
Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model
Tarun Gupta, Duc-Tuan Truong, Tran The Anh +1
The estimation of speaker characteristics such as age and height is a challenging task, having numerous applications in voice forensic analysis. In this work, we propose a bi-encod…
End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN
Manav Kaushik, Van Tung Pham, Eng Siong Chng
Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a nov…
Enriching Under-Represented Named-Entities To Improve Speech Recognition Performance
Tingzhi Mao, Yerbolat Khassanov, Van Tung Pham +4
Automatic speech recognition (ASR) for under-represented named-entity (UR-NE) is challenging due to such named-entities (NE) have insufficient instances and poor contextual coverag…