Multistream CNN for Robust Acoustic Modeling

05/21/2020
by   Kyu J. Han, et al.
0

This paper presents multistream CNN, a novel neural network architecture for robust acoustic modeling in speech recognition tasks. The proposed architecture accommodates diverse temporal resolutions in multiple streams to achieve robustness in acoustic modeling. For the diversity of temporal resolution in embedding processing, we consider dilation on TDNN-F, a variant of 1D-CNN. Each stream stacks narrower TDNN-F layers whose kernel has a unique, stream-specific dilation rate when processing input speech frames in parallel. Hence it can better represent acoustic events without the increase of model complexity. We validate the effectiveness of the proposed multistream CNN architecture by showing consistent improvement across various data sets. Trained with data augmentation methods, multistream CNN improves the WER of the test-other set in the LibriSpeech corpus by 12 production system for a contact center, it records a relative WER improvement of 11 customer channel recordings) to prove the superiority of the proposed model architecture in the wild. In terms of real-time factor (RTF), multistream CNN outperforms the normal TDNN-F by 15 production systems or applications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/21/2020

ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition

In this paper we present state-of-the-art (SOTA) performance on the Libr...
research
08/05/2021

MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription

This paper makes several contributions to automatic lyrics transcription...
research
11/11/2018

Multi-Temporal Resolution Convolutional Neural Networks for Acoustic Scene Classification

In this paper we present a Deep Neural Network architecture for the task...
research
07/11/2018

A Fast-Converged Acoustic Modeling for Korean Speech Recognition: A Preliminary Study on Time Delay Neural Network

In this paper, a time delay neural network (TDNN) based acoustic model i...
research
06/27/2017

Acoustic Modeling Using a Shallow CNN-HTSVM Architecture

High-accuracy speech recognition is especially challenging when large da...
research
12/21/2020

Multi-stream Convolutional Neural Network with Frequency Selection for Robust Speaker Verification

Speaker verification aims to verify whether an input speech corresponds ...
research
10/27/2022

A knowledge-driven vowel-based approach of depression classification from speech using data augmentation

We propose a novel explainable machine learning (ML) model that identifi...

Please sign up or login with your details

Forgot password? Click here to reset