In this work, we conduct a detailed evaluation of various allneural, end-to-end trained,
sequence-to-sequence models applied to the task of speech recognition. Notably, each of …

We introduce an encoder-decoder recurrent neural network model called Recurrent Neural
Aligner (RNA) that can be used for sequence to sequence mapping tasks. Like connectionist …

We investigate training end-to-end speech recognition models with the recurrent neural
network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture …

We train grapheme-based acoustic models for speech recognition using a hierarchical
recurrent neural network architecture with connectionist temporal classification (CTC) loss …

Recent work on end-to-end automatic speech recognition (ASR) has shown that the
connectionist temporal classification (CTC) loss can be used to convert acoustics to phone …

This paper presents a speech recognition system that directly transcribes audio data with
text, without requiring an intermediate phonetic representation. The system is based on a …

The choice of modeling units is critical to automatic speech recognition (ASR) tasks.
Conventional ASR systems typically choose context-dependent states (CD-states) or context …

Recently neural network acoustic models trained with Connectionist Temporal Classification
(CTC) were proposed as an alternative approach to conventional cross-entropy trained …

The connectionist temporal classification (CTC) loss function has several interesting
properties relevant for automatic speech recognition (ASR): applied on top of deep recurrent …

Utterance classification is a critical pre-processing step for many speech understanding and
dialog systems. In multi-user settings, one needs to first identify if an utterance is even …