Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Denis Filimonov"'
Autor:
Rahul Pandey, Roger Ren, Qi Luo, Jing Liu, Ariya Rastrow, Ankur Gandhe, Denis Filimonov, Grant Strimel, Andreas Stolcke, Ivan Bulyko
End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants often have difficulties recognizing infrequent words personalized to the user, such as names and places. Rare words often have non-trivial pronunciations, and in suc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f33cfd7f5039f3615dd10a65c9c5d3c
http://arxiv.org/abs/2303.17131
http://arxiv.org/abs/2303.17131
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
https://doi.org/10.1109/icassp39728.2021.9414800
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
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
Publikováno v:
INTERSPEECH
Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::523fe586ce2d253737171971cdc5d27d
http://arxiv.org/abs/1907.01677
http://arxiv.org/abs/1907.01677
Publikováno v:
SLT
In this paper, we explore the model combination problem for rescoring Automatic Speech Recognition (ASR) hypotheses. We use minimum Empirical Bayes Risk for the optimization criterion and Deterministic Annealing techniques to search through the non-c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb894e8a75810ae334ec981cc7e70c79
https://doi.org/10.1109/slt.2010.5700857
https://doi.org/10.1109/slt.2010.5700857
Autor:
Denis Filimonov, Mary Harper
Publikováno v:
Interspeech 2009.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::342ae774fb725f259c03e0d0cd1796f6
https://doi.org/10.21437/interspeech.2009-120
https://doi.org/10.21437/interspeech.2009-120
Autor:
Denis Filimonov, Mary P. Harper
Publikováno v:
EMNLP
We present a scalable joint language model designed to utilize fine-grain syntactic tags. We discuss challenges such a design faces and describe our solutions that scale well to large tagsets and corpora. We advocate the use of relatively simple tags
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea422c79dd1e1306a716174b87308362
https://doi.org/10.3115/1699648.1699657
https://doi.org/10.3115/1699648.1699657
Publikováno v:
ACM Transactions on Software Engineering & Methodology; Jul2024, Vol. 33 Issue 6, p1-33, 33p
Autor:
Pham, Van Tung, Xu, Haihua, Chen, Nancy F., Sivadas, Sunil, Lim, Boon Pang, Chng, Eng Siong, Li, Haizhou
Publikováno v:
2014 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2014, p7078-7082, 5p