LSTM-based language models for spontaneous speech recognition
I Medennikov, A Bulusheva - … 2016, Budapest, Hungary, August 23-27 …, 2016 - Springer
The language models (LMs) used in speech recognition to predict the next word (given the
context) often rely on too short context, which leads to recognition errors. In theory, using …
context) often rely on too short context, which leads to recognition errors. In theory, using …
Acoustic modeling in the STC keyword search system for OpenKWS 2016 evaluation
This paper describes in detail the acoustic modeling part of the keyword search system
developed in the Speech Technology Center (STC) for the OpenKWS 2016 evaluation. The …
developed in the Speech Technology Center (STC) for the OpenKWS 2016 evaluation. The …
Advances in STC Russian spontaneous speech recognition system
In this paper we present the latest improvements to the Russian spontaneous speech
recognition system developed in Speech Technology Center (STC). Significant word error …
recognition system developed in Speech Technology Center (STC). Significant word error …
Перенос знаний в задаче автоматического распознавания русской речи в телефонных переговорах
АН Романенко, ЮН Матвеев… - … технологий, механики и …, 2018 - cyberleninka.ru
Приведено описание метода переноса знаний (knowledge transfer) между ансамблем
нейросетевых акустических моделей и нейросетью-учеником. Данный метод …
нейросетевых акустических моделей и нейросетью-учеником. Данный метод …
Feature combination for the task of neural network acoustic model learning
AN Romanenko - Nauchno-Tekhnicheskii Vestnik …, 2018 - search.proquest.com
A method of feature combination for the problem of neural network acoustic models training
is proposed aimed at the quality improvement of speech recognition. Unlike the feeding of a …
is proposed aimed at the quality improvement of speech recognition. Unlike the feeding of a …
Knowledge transfer for Russian conversational telephone automatic speech recognition
This paper describes the method of knowledge transfer between the ensemble of neural
network acoustic models and student-network. This method is used to reduce computational …
network acoustic models and student-network. This method is used to reduce computational …
KNOWLEDGE TRANSFER FOR RUSSIAN CONVERSATIONAL TELEPHONE AUTOMATIC SPEECH RECOGNITION
N Romanenko Alexei, MY Nikolaevich… - Journal Scientific and …, 2018 - ntv.ifmo.ru
This paper describes the method of knowledge transfer between the ensemble of neural
network acoustic models and student-network. This method is used to reduce computational …
network acoustic models and student-network. This method is used to reduce computational …
Объединение признаков в задаче обучения нейросетевых акустических моделей
АН Романенко - Научно-технический вестник информационных …, 2018 - cyberleninka.ru
Предложен метод объединения признаков для задачи обучения нейросетевых
акустических моделей с целью повышения качества распознавания речи. В отличие от …
акустических моделей с целью повышения качества распознавания речи. В отличие от …