Advancing Connectionist Temporal Classification With Attention Modeling

03/15/2018
by   Amit Das, et al.
0

In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time convolution features to model attention as part of the CTC network. To further improve attention modeling, we utilize content information extracted from a network representing an implicit language model. Finally, we introduce vector based attention weights that are applied on context vectors across both time and their individual components. We evaluate our system on a 3400 hours Microsoft Cortana voice assistant task and demonstrate that our proposed model consistently outperforms the baseline model achieving about 20 reduction in word error rates.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/17/2021

Do End-to-End Speech Recognition Models Care About Context?

The two most common paradigms for end-to-end speech recognition are conn...
research
11/24/2019

Improving EEG based Continuous Speech Recognition

In this paper we introduce various techniques to improve the performance...
research
02/14/2020

Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR

We propose an unsupervised speaker adaptation method inspired by the neu...
research
09/04/2019

PaLM: A Hybrid Parser and Language Model

We present PaLM, a hybrid parser and neural language model. Building on ...
research
01/26/2022

Internal language model estimation through explicit context vector learning for attention-based encoder-decoder ASR

An end-to-end (E2E) speech recognition model implicitly learns a biased ...
research
12/31/2018

Advancing Acoustic-to-Word CTC Model with Attention and Mixed-Units

The acoustic-to-word model based on the Connectionist Temporal Classific...
research
06/11/2020

Implicit Kernel Attention

Attention compute the dependency between representations, and it encoura...

Please sign up or login with your details

Forgot password? Click here to reset