Search Results - "Bulyko, Ivan"

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

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

Mitigating Closed-Model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition by Yang, Chao-Han Huck, Ahmed, Zeeshan, Gu, Yile, Szurley, Joseph, Ren, Roger, Liu, Linda, Stolcke, Andreas, Bulyko, Ivan

“…In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. We focus on…”
Get full text

Towards Continual Entity Learning in Language Models for Conversational Agents by Gadde, Ravi Teja, Bulyko, Ivan

“…Neural language models (LM) trained on diverse corpora are known to work well on previously seen entities, however, updating these models with dynamically…”
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

Normalization of phonetic keyword search scores by Karakos, Damianos, Bulyko, Ivan, Schwartz, Richard, Tsakalidis, Stavros, Long Nguyen, Makhoul, John

“…As shown in [1, 2], score normalization is of crucial importance for improving the Average Term-Weighted Value (ATWV) measure that is commonly used for…”
Get full text

Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback by Lin, Guan-Ting, Shivakumar, Prashanth Gurunath, Gourav, Aditya, Gu, Yile, Gandhe, Ankur, Lee, Hung-yi, Bulyko, Ivan

“…While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language…”
Get full text

Discriminative Speech Recognition Rescoring with Pre-trained Language Models by Shivakumar, Prashanth Gurunath, Kolehmainen, Jari, Gu, Yile, Gandhe, Ankur, Rastrow, Ariya, Bulyko, Ivan

“…Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability…”
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

Multi-Modal Retrieval For Large Language Model Based Speech Recognition by Kolehmainen, Jari, Gourav, Aditya, Shivakumar, Prashanth Gurunath, Gu, Yile, Gandhe, Ankur, Rastrow, Ariya, Strimel, Grant, Bulyko, Ivan

“…Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language…”
Get full text

Personalization for BERT-based Discriminative Speech Recognition Rescoring by Kolehmainen, Jari, Gu, Yile, Gourav, Aditya, Shivakumar, Prashanth Gurunath, Gandhe, Ankur, Rastrow, Ariya, Bulyko, Ivan

“…Recognition of personalized content remains a challenge in end-to-end speech recognition. We explore three novel approaches that use personalized content in a…”
Get full text

Scaling Laws for Discriminative Speech Recognition Rescoring Models by Gu, Yile, Shivakumar, Prashanth Gurunath, Kolehmainen, Jari, Gandhe, Ankur, Rastrow, Ariya, Bulyko, Ivan

“…Recent studies have found that model performance has a smooth power-law relationship, or scaling laws, with training data and model size, for a wide range of…”
Get full text