Paper ID | SPE-9.6 | ||
Paper Title | END-TO-END MULTI-CHANNEL TRANSFORMER FOR SPEECH RECOGNITION | ||
Authors | Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris, Brian King, Siegfried Kunzmann, Amazon, United States | ||
Session | SPE-9: Speech Recognition 3: Transformer Models 1 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-LVCR] Large Vocabulary Continuous Recognition/Search | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectures for multi-channel speech recognition systems, where the spectral and spatial information collected from different microphones are integrated using attention layers. Our multi-channel transformer network mainly consists of three parts: channel-wise self attention layers (CSA), cross-channel attention layers (CCA), and multi-channel encoder-decoder attention layers (EDA). The CSA and CCA layers encode the contextual relationship "within" and "between" channels and across time, respectively. The channel-attended outputs from CSA and CCA are then fed into the EDA layers to help decode the next token given the preceding ones. The experiments show that in a far-field in-house dataset, our method outperforms the baseline single-channel transformer, as well as the super-directive and neural beamformers cascaded with the transformers. |