Martin Radfar

Multi-Channel Transformer Transducer for Speech Recognition

2021

Multi-channel inputs offer several advantages over singlechannel, to improve the robustness of on-device speech recognition systems.Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end ASR for improved accuracy.However, this …

End-to-End Spoken Language Understanding Using Joint CTC Loss and Self-Supervised, Pretrained Acoustic Encoders

2023

It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech recognition (ASR) models …