Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Michael Nirschl"'
Publikováno v:
ICASSP
Language Models (LMs) for Automatic Speech Recognition (ASR) can benefit from utilizing non-linguistic contextual signals in modeling. Examples of these signals include the geographical location of the user speaking to the system and/or the identity
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7408975e0b72ac2713b90b6aca52822
https://doi.org/10.1109/icassp.2018.8461979
https://doi.org/10.1109/icassp.2018.8461979
Publikováno v:
ICASSP
We present a new architecture and a training strategy for an adaptive mixture of experts with applications to domain robust language modeling. The proposed model is designed to benefit from the scenario where the training data are available in divers
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b03bda701e100b822cf184526a92f9b9
https://doi.org/10.1109/icassp.2018.8461628
https://doi.org/10.1109/icassp.2018.8461628
Autor:
Ananda Theertha Suresh, Michael Nirschl, Shankar Kumar, Daniel Holtmann-Rice, Hank Liao, Felix X. Yu
Publikováno v:
ASRU
Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f0324d80a067b7e96595e078ad9b99e
http://arxiv.org/abs/1711.05448
http://arxiv.org/abs/1711.05448
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7d5c07fc30b78ae15cbde80f5324316
https://doi.org/10.21437/interspeech.2017-1310
https://doi.org/10.21437/interspeech.2017-1310
Autor:
Michael Nirschl, H. Osborn
Superconformal Ward identities are derived for the the four point functions of chiral primary BPS operators for $\N=2,4$ superconformal symmetry in four dimensions. Manipulations of arbitrary tensorial fields are simplified by introducing a null vect
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80bb9e5d014079a6293a82a886932e15