Výsledky vyhledávání

Domain-Aware Neural Language Models for Speech Recognition

Autor: Aditya Gourav, Ankur Gandhe, Denis Filimonov, Linda Liu, Ariya Rastrow, Ivan Bulyko, Shashank Kalmane, Yile Gu

Publikováno v: ICASSP

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. We present a domain-aware rescoring framework suitable for achieving domain-adaptation dur

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2fc6c07a31c2fb935f91ff085c0cb777
https://doi.org/10.1109/icassp39728.2021.9414800

Zobrazit plný text záznamu

Personalization Strategies for End-to-End Speech Recognition Systems

Autor: Yile Gu, Gautam Tiwari, Ivan Bulyko, Shashank Kalmane, Linda Liu, Andreas Stolcke, Guitang Lan, Xiangyang Huang, Denis Filimonov, Ankur Gandhe, Ariya Rastrow, Aditya Gourav

Publikováno v: ICASSP

The recognition of personalized content, such as contact names, remains a challenging problem for end-to-end speech recognition systems. In this work, we demonstrate how first and second-pass rescoring strategies can be leveraged together to improve

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b478fe456c395d84b6ae8a16f4a1ab7a

Zobrazit plný text záznamu

Attention-based Contextual Language Model Adaptation for Speech Recognition

Autor: Ariya Rastrow, Ivan Bulyko, Ankur Gandhe, Andreas Stolcke, Scott Novotney, Richard Diehl Martinez

Publikováno v: ACL/IJCNLP (Findings)

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance was spoken,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ae87029e06fe835d4cd27f5e1e906b9

Zobrazit plný text záznamu

Multi-task Language Modeling for Improving Speech Recognition of Rare Words

Autor: Chao-Han Huck Yang, Linda Liu, Ankur Gandhe, Yile Gu, Anirudh Raju, Denis Filimonov, Ivan Bulyko

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the performance on rare

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4b1f046eb5c9be44b06e0e17e81e914e

Zobrazit plný text záznamu

Web resources for language modeling in conversational speech recognition

Autor: Mari Ostendorf, Ivan Bulyko, Özgür Çetin, Andreas Stolcke, Tim Ng, Man-Hung Siu

Publikováno v: ACM Transactions on Speech and Language Processing. 5:1-25

This article describes a methodology for collecting text from the Web to match a target sublanguage both in style (register) and topic. Unlike other work that estimates n-gram statistics from page counts, the approach here is to select and filter doc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4286f2401b7cd053dcc49e240297c0bf
https://doi.org/10.1145/1322391.1322392

Zobrazit plný text záznamu

Error-correction detection and response generation in a spoken dialogue system

Autor: J. Goldberg, Mari Ostendorf, Katrin Kirchhoff, Ivan Bulyko

Publikováno v: Speech Communication. 45:271-288

Speech understanding errors in spoken dialogue systems can be frustrating for users and difficult to recover from in a mixed-initiative spoken dialogue system. Handling such errors requires both detecting error conditions and adjusting the response g

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cbe4008fd3dd321ad5258967e53118cf
https://doi.org/10.1016/j.specom.2004.09.009

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání