AI Chat

Language Identification with Deep Bottleneck Features

09/18/2018

∙

by Zhanyu Ma, et al.

∙

∙

In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features used for LSTM learning are generated by a transfer learning method. Bottle-neck features of a deep neural network (DNN) which are trained for mandarin acoustic-phonetic classification are used for LSTM training. In order to improve the SLD accuracy of short utterances a phase vocoder based time-scale modification(TSM) method is used to reduce and increase speech rated of the test utterance. By splicing the normal, speech rate reduced and increased utterances, we can extend length of test utterances so as to improved improved the performance of the SLD system. The experimental results on AP17-OLR database shows that the proposed methods can improve the performance of SLD, especially on short utterance with 1s and 3s durations.

Zhanyu Ma
62 publications
Hong Yu
55 publications

page 3

page 4

∙ 09/20/2018

LSTM-based Whisper Detection

This article presents a whisper speech detector in the far-field domain....

0 Zeynab Raeesy, et al. ∙

∙ 01/02/2019

A Deep Learning Approach for Similar Languages, Varieties and Dialects

Deep learning mechanisms are prevailing approaches in recent days for th...

0 Vidya Prasad K, et al. ∙

∙ 02/22/2016

Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Generation Error Training

We propose two novel techniques --- stacking bottleneck features and min...

0 Zhizheng Wu, et al. ∙

∙ 04/12/2021

End-to-End Mandarin Tone Classification with Short Term Context Information

In this paper, we propose an end-to-end Mandarin tone classification met...

0 Jiyang Tang, et al. ∙

∙ 07/06/2019

Towards Debugging Deep Neural Networks by Generating Speech Utterances

Deep neural networks (DNN) are able to successfully process and classify...

0 Bilal Soomro, et al. ∙

∙ 05/09/2017

Phonetic Temporal Neural Model for Language Identification

Deep neural models, particularly the LSTM-RNN model, have shown great po...

0 Zhiyuan Tang, et al. ∙

∙ 12/19/2019

LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge

This paper presents a novel Dialect Identification (DID) system develope...

0 Xiaoxiao Miao, et al. ∙