Search Results for author:
Found 7 papers, 0 papers with code
Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systems
In this work, we propose a contextual density ratio approach for both training a contextual aware E2E model and adapting the language model to named entities.
On the Prediction Network Architecture in RNN-T for ASR
In contrast to some previous works, our results show that Transformer does not always outperform LSTM when used as prediction network along with Conformer encoder.
Conformer with dual-mode chunked attention for joint online and offline ASR
In the dual-mode Conformer Transducer model, layers can function in online or offline mode while sharing parameters, and in-place knowledge distillation from offline to online mode is applied in training to improve online accuracy.
ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization
End-to-end (E2E) multi-channel ASR systems show state-of-the-art performance in far-field ASR tasks by joint training of a multi-channel front-end along with the ASR model.
Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition
We use a single-channel encoder for CT speech and a multi-channel encoder with Spatial Filtering neural beamforming for FT speech, which are jointly trained with the encoder selection.
Semi-Supervised Learning with Data Augmentation for End-to-End ASR
In the result, the Noisy Student algorithm with soft labels and consistency regularization achieves 10. 4% word error rate (WER) reduction when adding 475h of unlabeled data, corresponding to a recovery rate of 92%.
Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity.
