Analysis of Multilingual Sequence-to-Sequence speech recognition systems

11/07/2018
by   Martin Karafiat, et al.
0

This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic speech recognition (ASR). On a set composed of Babel data, we first show the effectiveness of multi-lingual training with stacked bottle-neck (SBN) features. Then we explore various architectures and training strategies of multi-lingual seq2seq models based on CTC-attention networks including combinations of output layer, CTC and/or attention component re-training. We also investigate the effectiveness of language-transfer learning in a very low resource scenario when the target language is not included in the original multi-lingual training data. Interestingly, we found multilingual features superior to multilingual models, and this finding suggests that we can efficiently combine the benefits of the HMM system with the seq2seq system through these multilingual feature techniques.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/04/2018

Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...
research
05/28/2022

Adaptive Activation Network For Low Resource Multilingual Speech Recognition

Low resource automatic speech recognition (ASR) is a useful but thorny t...
research
06/12/2018

Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages

Sequence-to-sequence attention-based models integrate an acoustic, pronu...
research
02/21/2018

Sequence-based Multi-lingual Low Resource Speech Recognition

Techniques for multi-lingual and cross-lingual speech recognition can he...
research
11/06/2018

Language model integration based on memory control for sequence to sequence speech recognition

In this paper, we explore several new schemes to train a seq2seq model t...
research
05/14/2022

Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challenge

This paper investigates different pretraining approaches to spoken langu...
research
10/23/2020

Speech Activity Detection Based on Multilingual Speech Recognition System

To better model the contextual information and increase the generalizati...

Please sign up or login with your details

Forgot password? Click here to reset