DeepAI AI Chat
Log In Sign Up

Back from the future: bidirectional CTC decoding using future information in speech recognition

10/07/2021
by   Namkyu Jung, et al.
0

In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future as well as the past information in order to predict the next output in the sequence. The proposed method based on bi-directional beam search takes advantage of the CTC greedy decoding output to represent the noisy future information. Experiments on the Librispeechdataset demonstrate the superiority of our proposed method compared to baselines using unidirectional decoding. In particular, the boost inaccuracy is most apparent at the start of a sequence which is the most erroneous part for existing systems based on unidirectional decoding.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/31/2022

Blank Collapse: Compressing CTC emission for the faster decoding

Connectionist Temporal Classification (CTC) model is a very efficient me...
08/18/2020

Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation

False triggers in voice assistants are unintended invocations of the ass...
10/23/2019

Efficient Dynamic WFST Decoding for Personalized Language Models

We propose a two-layer cache mechanism to speed up dynamic WFST decoding...
11/06/2022

Suffix Retrieval-Augmented Language Modeling

Causal language modeling (LM) uses word history to predict the next word...
08/12/2014

First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs

We present a method to perform first-pass large vocabulary continuous sp...
03/21/2022

Enhancing Speech Recognition Decoding via Layer Aggregation

Recently proposed speech recognition systems are designed to predict usi...
05/24/2017

Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning

We develop the first approximate inference algorithm for 1-Best (and M-B...