Search Results for author:
Found 13 papers, 6 papers with code
Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models
Neural networks have been successfully used for non-intrusive speech intelligibility prediction.
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
Convolution augmented transformers (conformers) have performed well for many speech processing tasks but have been under-researched for speech separation.
Ranked #3 on
Speech Separation
on WHAMR!
The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions
In this work, SE models are trained and tested on a number of different languages, with self-supervised representations which themselves are trained using different language combinations and with differing network structures as loss function representations.
Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations
Self-supervised speech representations (SSSRs) have been successfully applied to a number of speech-processing tasks, e. g. as feature extractor for speech quality (SQ) prediction, which is, in turn, relevant for assessment and training speech enhancement systems for users with normal or impaired hearing.
CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation
In this paper, we propose a novel context-aware graph-attention model (Context-aware GAT), which can effectively incorporate global features of relevant knowledge graphs based on a context-enhanced knowledge aggregation process.
On Data Sampling Strategies for Training Neural Network Speech Separation Models
In this work, the impact of applying these training signal length (TSL) limits is analysed for two speech separation models: SepFormer, a transformer model, and Conv-TasNet, a convolutional model.
Perceive and predict: self-supervised speech representation based loss functions for speech enhancement
Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models.
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
In this work deformable convolution is proposed as a solution to allow TCN models to have dynamic RFs that can adapt to various reverberation times for reverberant speech separation.
Ranked #12 on
Speech Separation
on WHAMR!
Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation
It is shown that this weighted multi-dilation temporal convolutional network (WD-TCN) consistently outperforms the TCN across various model configurations and using the WD-TCN model is a more parameter efficient method to improve the performance of the model than increasing the number of convolutional blocks.
Ranked #1 on
Speech Dereverberation
on WHAMR!
Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation
A feature of TCNs is that they have a receptive field (RF) dependent on the specific model configuration which determines the number of input frames that can be observed to produce an individual output frame.
Ranked #1 on
Speech Dereverberation
on WHAMR_ext
MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data
Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results.
