Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

INVESTIGATION OF MULTILINGUAL DEEP NEURAL NETWORKS FOR SPOKEN TERM DETECTION

Domain:

natural language processing

Record type:

paper
Creator:
KniGalRatWoo
Editor:
ApoUni
Publisher:
Ins
Host:avatar
The development of high-performance speech processing systems for low-resource languages is a challenging area. One approach to address the lack of resources is to make use of data from multiple languages. A popular direction in recent years is to use bottleneck features, or hybrid systems, trained on multilingual data for speech-to-text (STT) systems. This paper presents an investigation into the application of these multilingual approaches to spoken term detection. Experiments were run using the IARPA Babel limited language pack corpora (~10 hours/language) with 4 languages for initial multilingual system development and an additional held-out target language. STT gains achieved through using multilingual bottleneck features in a Tandem configuration are shown to also apply to keyword search (KWS). Further improvements in both STT and KWS were observed by incorporating language questions into the Tandem GMM-HMM decision trees for the training set languages. Adapted hybrid systems performed slightly worse on average than the adapted Tandem systems. A language independent acoustic model test on the target language showed that retraining or adapting of the acoustic models to the target language is currently minimally needed to achieve reasonable performance.

Visit

doi.orgwww.repository.cam.ac.uk

Tasks

automatic speech recognitionkeywordsspeech processing

Tags

4605 Data Management and Data Science46 Information and Computing Sciences47 Language, Communication and Culture4704 Linguistics

Similar

Malaria Cell Detection Using Deep Neural NetworksQuery-by-example Spoken Term Detection using Attention-based Multi-hop NetworksShort-Term Load Forecasting Based on CNN and LSTM Deep Neural NetworksDeep convolutional neural networks for remote sensing investigation of looting of the archeological site of Al-Lisht, EgyptCode-switched English Pronunciation Modeling for Swahili Spoken Term DetectionDetection of Degraded Acacia tree species using deep neural networks on uav drone imagery

Malaria Cell Detection Using Deep Neural Networks

Malaria remains one of the most pressing public health concerns globally, causing significant morbid

Query-by-example Spoken Term Detection using Attention-based Multi-hop Networks

Retrieving spoken content with spoken queries, or query-by- example spoken term detection (STD), is

Short-Term Load Forecasting Based on CNN and LSTM Deep Neural Networks

International audience In the coming years, the world will witness a global transitio

Deep convolutional neural networks for remote sensing investigation of looting of the archeological site of Al-Lisht, Egypt

Looting of archaeological sites is a global problem. To quantify looting on a nationwide scale and t

Code-switched English Pronunciation Modeling for Swahili Spoken Term Detection

Detection of Degraded Acacia tree species using deep neural networks on uav drone imagery

Deep-learning-based image classification and object detection has been applied successfully to tree