2 papers
eess.AS2018
Deep Segment Attentive Embedding for Duration Robust Speaker Verification
Bin Liu, Shuai Nie, Yaping Zhang +2
LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the avera…
cs.SD2018
Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training
Bin Liu, Shuai Nie, Yaping Zhang +3
In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) system…