This paper introduces contrastive siamese (c-siam) network, an architect...
In this paper, we present a novel speaker diarization system for streami...
Reducing prediction delay for streaming end-to-end ASR models with minim...
In this paper we present a Transformer-Transducer model architecture and...
This article describes a density ratio approach to integrating external
...
In this paper we present an end-to-end speech recognition model with
Tra...
Multilingual training has been shown to improve acoustic modeling perfor...
This work presents a scalable solution to open-vocabulary visual speech
...
We investigate training end-to-end speech recognition models with the
re...
In this paper we document our experiences with developing speech recogni...
We present results that show it is possible to build a competitive, grea...
We describe a large vocabulary speech recognition system that is accurat...
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent...
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN)
archit...