5 citations · 11 across the 6 of their papers we have counts for
6 papers
Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systems
Jesús Andrés-Ferrer, Dario Albesano, Puming Zhan +1
End-2-end (E2E) models have become increasingly popular in some ASR tasks because of their performance and advantages. These E2E models directly approximate the posterior distribut…
Conformer with dual-mode chunked attention for joint online and offline ASR
Felix Weninger, Marco Gaudesi, Md Akmal Haidar +3
In this paper, we present an in-depth study on online attention mechanisms and distillation techniques for dual-mode (i.e., joint online and offline) ASR using the Conformer Transd…
ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization
Marco Gaudesi, Felix Weninger, Dushyant Sharma +1
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. The mai…
Dual-Encoder Architecture with Encoder Selection for Joint Close-Talk and Far-Talk Speech Recognition
Felix Weninger, Marco Gaudesi, Ralf Leibold +2
In this paper, we propose a dual-encoder ASR architecture for joint modeling of close-talk (CT) and far-talk (FT) speech, in order to combine the advantages of CT and FT devices fo…
Semi-Supervised Learning with Data Augmentation for End-to-End ASR
Felix Weninger, Franco Mana, Roberto Gemello +2
In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization pr…
Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
Felix Weninger, Jesús Andrés-Ferrer, Xinwei Li +1
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done…