This paper proposes a simple yet effective model-based neural network speaker adaptation
technique that learns speaker-specific hidden unit contributions given adaptation data …

The use of context-dependent targets has become standard in hybrid DNN systems for
automatic speech recognition. However, we argue that despite the use of state-tying …

Recurrent neural network language models (RNNLMs) have been shown to consistently
improve Word Error Rates (WERs) of large vocabulary speech recognition systems …

This paper describes the ALISA tool, which implements a lightly supervised method for
sentence-level alignment of speech with imperfect transcripts. Its intended use is to enable …

We present a method for mining the web for text entered on mobile devices. Using
searching, crawling, and parsing techniques, we locate text that can be reliably identified as …

Аннотация В статье представлен аналитический обзор основных разновидностей
акустических и языковых моделей на основе искусственных нейронных сетей для …

Self-training is a simple and efficient way of leveraging un-labeled speech data:(i) start with
a seed system trained on transcribed speech;(ii) pass the unlabeled data through this seed …

This paper proposes an algorithm to design a tied-state inventory for a context dependent,
neural network-based acoustic model for speech recognition. Rather than relying on a …

We propose an algorithm that allows online training of a context dependent DNN model. It
designs a state inventory based on DNN features and jointly optimizes the DNN parameters …

Lectures are usually known to be highly specialised in that they deal with multiple and
domain specific topics. This context is challenging for Automatic Speech Recognition (ASR) …