AIConfPaper
← Search

Ross McGowan

4 accepted papers

2023

Dialog Act Guided Contextual Adapter for Personalized Speech Recognition

Feng-Ju Chang, Thejaswi Muniyappa, Kanthashree Mysore Sathyendra, Kai Wei, Grant P. Strimel, Ross McGowan
ICASSP 2023accepted

Personalization in multi-turn dialogs has been a long standing challenge for end-to-end automatic speech recognition (E2E ASR) models. Recent work on contextual adapters has tackled rare word recognition using user catalogs. This adaptation, however, does not incorporate an important cue, the dialog…

Cited by 0Source ↗Scholar ↗
2023

Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition

Saumya Y. Sahai, Jing Liu, Thejaswi Muniyappa, Kanthashree Mysore Sathyendra, Anastasios Alexandridis, Grant P. Strimel +5
ICASSP 2023accepted

We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This architecture enables a dynamic switch for its runtime compute paths by exploiting WW spotting to select which branch of its att…

Cited by 0Source ↗Scholar ↗
2023

Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition

Xuandi Fu, Kanthashree Mysore Sathyendra, Ankur Gandhe, Jing Liu, Grant P. Strimel, Ross McGowan +1
ICASSP 2023accepted

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These approaches employ crossattention to bias the model towards specific c…

Cited by 0Source ↗Scholar ↗
2022

Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding

Bhuvan Agrawal, Markus Müller, Samridhi Choudhary, Martin Radfar, Athanasios Mouchtaris, Ross McGowan +2
ICASSP 2022accepted

End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we consider an E2E system as a mul…

Cited by 0Source ↗Scholar ↗