Search Results - "Sathyendra, Kanthashree Mysore"

Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition by 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…”
Get full text

Dialog Act Guided Contextual Adapter for Personalized Speech Recognition by 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…”
Get full text

Gated Contextual Adapters For Selective Contextual Biasing In Neural Transducers by Alexandridis, Anastasios, Sathyendra, Kanthashree Mysore, Strimel, Grant P., Chang, Feng-Ju, Rastrow, Ariya, Susanj, Nathan, Mouchtaris, Athanasios

“…Neural contextual biasing for end-to-end neural ASR transducers has shown significant improvements in the recognition of named entities, such as contact names…”
Get full text

Contextual Adapters for Personalized Speech Recognition in Neural Transducers by Sathyendra, Kanthashree Mysore, Muniyappa, Thejaswi, Chang, Feng-Ju, Liu, Jing, Su, Jinru, Strimel, Grant P., Mouchtaris, Athanasios, Kunzmann, Siegfried

“…Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to…”
Get full text

TINYS2I: A Small-Footprint Utterance Classification Model with Contextual Support for On-Device SLU by Alexandridis, Anastasios, Sathyendra, Kanthashree Mysore, Strimel, Grant P., Kveton, Pavel, Webb, Jon, Mouchtaris, Athanasios

“…On-device spoken language understanding (SLU) offers the potential for significant latency savings compared to cloud-based processing, as the audio stream does…”
Get full text

Multi-Task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding by Fu, Xuandi, Chang, Feng-Ju, Radfar, Martin, Wei, Kai, Liu, Jing, Strimel, Grant P., Sathyendra, Kanthashree Mysore

“…End-to-end Spoken Language Understanding (E2E SLU) has attracted increasing interest due to its advantages of joint optimization and low latency when compared…”
Get full text

Multilingual Grapheme-To-Phoneme Conversion with Byte Representation by Yu, Mingzhi, Nguyen, Hieu Duy, Sokolov, Alex, Lepird, Jack, Sathyendra, Kanthashree Mysore, Choudhary, Samridhi, Mouchtaris, Athanasios, Kunzmann, Siegfried

“…Grapheme-to-phoneme (G2P) models convert a written word into its corresponding pronunciation and are essential components in automatic-speech-recognition and…”
Get full text

Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition by 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…”
Get full text

Dialog act guided contextual adapter for personalized speech recognition by 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…”
Get full text

Extreme Model Compression for On-device Natural Language Understanding by Sathyendra, Kanthashree Mysore, Choudhary, Samridhi, Nicolich-Henkin, Leah

“…In this paper, we propose and experiment with techniques for extreme compression of neural natural language understanding (NLU) models, making them suitable…”
Get full text

Contextual Adapters for Personalized Speech Recognition in Neural Transducers by Sathyendra, Kanthashree Mysore, Muniyappa, Thejaswi, Chang, Feng-Ju, Liu, Jing, Su, Jinru, Strimel, Grant P, Mouchtaris, Athanasios, Kunzmann, Siegfried

“…Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to…”
Get full text

Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding by Fu, Xuandi, Chang, Feng-Ju, Radfar, Martin, Wei, Kai, Liu, Jing, Strimel, Grant P, Sathyendra, Kanthashree Mysore

“…End-to-end Spoken Language Understanding (E2E SLU) has attracted increasing interest due to its advantages of joint optimization and low latency when compared…”
Get full text

Statistical Model Compression for Small-Footprint Natural Language Understanding by Strimel, Grant P, Sathyendra, Kanthashree Mysore, Peshterliev, Stanislav

“…In this paper we investigate statistical model compression applied to natural language understanding (NLU) models. Small-footprint NLU models are important for…”
Get full text

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

“…ASRU2021 Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots…”
Get full text

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

“…Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from…”
Get full text

Gated-Attention Architectures for Task-Oriented Language Grounding by Chaplot, Devendra Singh, Sathyendra, Kanthashree Mysore, Pasumarthi, Rama Kumar, Rajagopal, Dheeraj, Salakhutdinov, Ruslan

“…To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it…”
Get full text