Search Results for author:
Found 9 papers, 1 papers with code
T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
The use of memory mechanism could reach 10. 6% and 7. 7% relative improvement compared with not using memory mechanism.
Towards Low-Resource StarGAN Voice Conversion using Weight Adaptive Instance Normalization
In this work, we aim at improving the data efficiency of the model and achieving a many-to-many non-parallel StarGAN-based voice conversion for a relatively large number of speakers with limited training samples.
Sound Audio and Speech Processing
Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
To evaluate the effectiveness of the proposed approach, artificial datasets based on Switchboard Cellular part1 (SWBC) and Voxceleb1 are constructed in two conditions, where speakers' voices are overlapped and not overlapped.
Speaker Re-identification with Speaker Dependent Speech Enhancement
The obtained results show that the proposed approach using speaker dependent speech enhancement can yield better speaker recognition and speech enhancement performances than two baselines in various noise conditions.
Robust Speaker Recognition Using Speech Enhancement And Attention Model
Instead of individually processing speech enhancement and speaker recognition, the two modules are integrated into one framework by a joint optimisation using deep neural networks.
Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
The proposed approach separates different speaker properties from a two-speaker signal in embedding space.
H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
In the proposed approach, frame-level encoder and attention are applied on segments of an input utterance and generate individual segment vectors.
Contextual Joint Factor Acoustic Embeddings
To evaluate the effectiveness of our approaches compared to prior work, two tasks are conducted -- phone classification and speaker recognition -- and test on different TIMIT data sets.
Improving Noise Robustness In Speaker Identification Using A Two-Stage Attention Model
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments.
