Search Results - "Gandhe, Ankur"

Audio-Attention Discriminative Language Model for ASR Rescoring by Gandhe, Ankur, Rastrow, Ariya

“…End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream…”
Get full text

Usted: Improving ASR with a Unified Speech and Text Encoder-Decoder by Yusuf, Bolaji, Gandhe, Ankur, Sokolov, Alex

“…Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training…”
Get full text

RescoreBERT: Discriminative Speech Recognition Rescoring With Bert by Xu, Liyan, Gu, Yile, Kolehmainen, Jari, Khan, Haidar, Gandhe, Ankur, Rastrow, Ariya, Stolcke, Andreas, Bulyko, Ivan

“…Second-pass rescoring is an important component in automatic speech recognition (ASR) systems that is used to improve the outputs from a first-pass decoder by…”
Get full text

On-the-Fly Text Retrieval for end-to-end ASR Adaptation by Yusuf, Bolaji, Gourav, Aditya, Gandhe, Ankur, Bulyko, Ivan

“…End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language…”
Get full text

A Likelihood Ratio Based Domain Adaptation Method for E2E Models by Choudhury, Chhavi, Gandhe, Ankur, Ding, Xiaohan, Bulyko, Ivan

“…End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR…”
Get full text

Personalization Strategies for End-to-End Speech Recognition Systems by Gourav, Aditya, Liu, Linda, Gandhe, Ankur, Gu, Yile, Lan, Guitang, Huang, Xiangyang, Kalmane, Shashank, Tiwari, Gautam, Filimonov, Denis, Rastrow, Ariya, Stolcke, Andreas, Bulyko, Ivan

“…The recognition of personalized content, such as contact names, remains a challenging problem for end-to-end speech recognition systems. In this work, we…”
Get full text

Domain-Aware Neural Language Models for Speech Recognition by Liu, Linda, Gu, Yile, Gourav, Aditya, Gandhe, Ankur, Kalmane, Shashank, Filimonov, Denis, Rastrow, Ariya, Bulyko, Ivan

“…As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains…”
Get full text

Lattention: Lattice-Attention in ASR Rescoring by Pandey, Prabhat, Torres, Sergio Duarte, Bayer, Ali Orkan, Gandhe, Ankur, Leutnant, Volker

“…Lattices form a compact representation of multiple hypotheses generated from an automatic speech recognition system and have been shown to improve performance…”
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

Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue by Lin, Guan-Ting, Shivakumar, Prashanth Gurunath, Gandhe, Ankur, Yang, Chao-Han Huck, Gu, Yile, Ghosh, Shalini, Stolcke, Andreas, Lee, Hung-Yi, Bulyko, Ivan

“…Large Language Models (LLMs) have demonstrated superior abilities in tasks such as chatting, reasoning, and question-answering. However, standard LLMs may…”
Get full text

Procter: Pronunciation-Aware Contextual Adapter For Personalized Speech Recognition In Neural Transducers by Pandey, Rahul, Ren, Roger, Luo, Qi, Liu, Jing, Rastrow, Ariya, Gandhe, Ankur, Filimonov, Denis, Strimel, Grant, Stolcke, Andreas, Bulyko, Ivan

“…End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants often have difficulties recognizing infrequent words personalized to the…”
Get full text

Towards ASR Robust Spoken Language Understanding Through in-Context Learning with Word Confusion Networks by Everson, Kevin, Gu, Yile, Yang, Huck, Shivakumar, Prashanth Gurunath, Lin, Guan-Ting, Kolehmainen, Jari, Bulyko, Ivan, Gandhe, Ankur, Ghosh, Shalini, Hamza, Wael, Lee, Hung-Yi, Rastrow, Anya, Stolcke, Andreas

“…In the realm of spoken language understanding (SLU). numerous natural language understanding (NLU) methodologies have been adapted by supplying large language…”
Get full text

Scalable Language Model Adaptation for Spoken Dialogue Systems by Gandhe, Ankur, Rastrow, Ariya, Hoffmeister, Bjorn

“…Language models (LM) for interactive speech recognition systems are trained on large amounts of data and the model parameters are optimized on past user data…”
Get full text

Optimization of Neural Network Language Models for keyword search by Gandhe, Ankur, Metze, Florian, Waibel, Alex, Lane, Ian

“…Recent works have shown Neural Network based Language Models (NNLMs) to be an effective modeling technique for Automatic Speech Recognition. Prior works have…”
Get full text

Audio-attention discriminative language model for ASR rescoring by Gandhe, Ankur, Rastrow, Ariya

“…End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream…”
Get full text

USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder by Yusuf, Bolaji, Gandhe, Ankur, Sokolov, Alex

“…Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training…”
Get full text

Streaming Speech-to-Confusion Network Speech Recognition by Filimonov, Denis, Pandey, Prabhat, Rastrow, Ariya, Gandhe, Ankur, Stolcke, Andreas

“…Proc. Interspeech, Aug. 2023, pp. 4099-4103 In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search…”
Get full text

On-the-fly Text Retrieval for End-to-End ASR Adaptation by Yusuf, Bolaji, Gourav, Aditya, Gandhe, Ankur, Bulyko, Ivan

“…End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language…”
Get full text

Speech Recognition Rescoring with Large Speech-Text Foundation Models by Shivakumar, Prashanth Gurunath, Kolehmainen, Jari, Gourav, Aditya, Gu, Yi, Gandhe, Ankur, Rastrow, Ariya, Bulyko, Ivan

“…Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition…”
Get full text

Multi-Task Language Modeling for Improving Speech Recognition of Rare Words by Yang, Chao-Han Huck, Liu, Linda, Gandhe, Ankur, Gu, Yile, Raju, Anirudh, Filimonov, Denis, Bulyko, Ivan

“…End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance…”
Get full text