The CAPIO 2017 conversational speech recognition system
In this paper we show how we have achieved the state-of-the-art performance on the
industry-standard NIST 2000 Hub5 English evaluation set. We explore densely connected …
industry-standard NIST 2000 Hub5 English evaluation set. We explore densely connected …
Neural network language modeling with letter-based features and importance sampling
In this paper we describe an extension of the Kaldi software toolkit to support neural-based
language modeling, intended for use in automatic speech recognition (ASR) and related …
language modeling, intended for use in automatic speech recognition (ASR) and related …
Recurrent neural network language model training with noise contrastive estimation for speech recognition
In recent years recurrent neural network language models (RNNLMs) have been
successfully applied to a range of tasks including speech recognition. However, an …
successfully applied to a range of tasks including speech recognition. However, an …
Efficient training and evaluation of recurrent neural network language models for automatic speech recognition
Recurrent neural network language models (RNNLMs) are becoming increasingly popular
for a range of applications including automatic speech recognition. An important issue that …
for a range of applications including automatic speech recognition. An important issue that …
Scalable multi corpora neural language models for asr
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 …
language models by a substantial margin in Automatic Speech Recognition (ASR) and other …
Lattice rescoring strategies for long short term memory language models in speech recognition
S Kumar, M Nirschl, D Holtmann-Rice… - 2017 IEEE Automatic …, 2017 - ieeexplore.ieee.org
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 …
(LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs …
Automatic speech recognition with very large conversational finnish and estonian vocabularies
Today, the vocabulary size for language models in large vocabulary speech recognition is
typically several hundreds of thousands of words. While this is already sufficient in some …
typically several hundreds of thousands of words. While this is already sufficient in some …
[PDF][PDF] Deep Learning-Based Telephony Speech Recognition in the Wild.
In this paper, we explore the effectiveness of a variety of Deep Learning-based acoustic
models for conversational telephony speech, specifically TDNN, bLSTM and CNN-bLSTM …
models for conversational telephony speech, specifically TDNN, bLSTM and CNN-bLSTM …
Improving the training and evaluation efficiency of recurrent neural network language models
Recurrent neural network language models (RNNLMs) are becoming increasingly popular
for speech recognition. Previously, we have shown that RNNLMs with a full (non-classed) …
for speech recognition. Previously, we have shown that RNNLMs with a full (non-classed) …
[PDF][PDF] Densely Connected Networks for Conversational Speech Recognition.
In this paper we show how we have achieved the state-of-theart performance on the industry-
standard NIST 2000 Hub5 English evaluation set. We propose densely connected LSTMs …
standard NIST 2000 Hub5 English evaluation set. We propose densely connected LSTMs …