Výsledky vyhledávání - "McGowan, Ross A."

Report

Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition

Autor: Fu, Xuandi, Sathyendra, Kanthashree Mysore, Gandhe, Ankur, Liu, Jing, Strimel, Grant P., McGowan, Ross, Mouchtaris, Athanasios

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 c

Externí odkaz: http://arxiv.org/abs/2305.05271

Zobrazit plný text záznamu

Report

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

Autor: Sahai, Saumya Y., Liu, Jing, Muniyappa, Thejaswi, Sathyendra, Kanthashree M., Alexandridis, Anastasios, Strimel, Grant P., McGowan, Ross, Rastrow, Ariya, Chang, Feng-Ju, Mouchtaris, Athanasios, Kunzmann, Siegfried

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 exploi

Externí odkaz: http://arxiv.org/abs/2304.01905

Zobrazit plný text záznamu

Report

Dialog act guided contextual adapter for personalized speech recognition

Autor: Chang, Feng-Ju, Muniyappa, Thejaswi, Sathyendra, Kanthashree Mysore, Wei, Kai, Strimel, Grant P., McGowan, Ross

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,

Externí odkaz: http://arxiv.org/abs/2303.17799

Zobrazit plný text záznamu

Report

Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding

Autor: Wei, Kai, Tran, Thanh, Chang, Feng-Ju, Sathyendra, Kanthashree Mysore, Muniyappa, Thejaswi, Liu, Jing, Raju, Anirudh, McGowan, Ross, Susanj, Nathan, Rastrow, Ariya, Strimel, Grant P.

Publikováno v: ASRU2021

Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional text-based natu

Externí odkaz: http://arxiv.org/abs/2112.06743

Zobrazit plný text záznamu