Multilingual MRASTA features for low-resource keyword search and speech recognition systems

No abstract is available for this paper.

• Publication year

  2014

• Venue

  IEEE International Conference on Acoustics, Speech, and Signal Processing

• Publication date

  2014-05-04

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1109/ICASSP.2014.6855129
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multilingual hierarchical MRASTA features for ASR

  2013cited by this paper
• Deep hierarchical bottleneck MRASTA features for LVCSR

  2013cited by this paper
• Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions

  2013cited by this paper
• Multilingual multilayer perceptron for rapid language adaptation between and across language families

  2013cited by this paper
• A high-performance Cantonese keyword search system

  2013cited by this paper
• Multilingual acoustic models using distributed deep neural networks

  2013cited by this paper
• Exploiting diversity for spoken term detection

  2013cited by this paper
• Multilingual training of deep neural networks

  2013cited by this paper
• The language-independent bottleneck features

  2012influential reference
• Multilingual MLP features for low-resource LVCSR systems

  2012cited by this paper
• On the Estimation of Discount Parameters for Language Model Smoothing

  2011cited by this paper
• RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit

  2011cited by this paper
• Convolutive Bottleneck Network features for LVCSR

  2011cited by this paper
• Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription

  2011cited by this paper
• Hierarchical bottle neck features for LVCSR

  2010cited by this paper
• Towards mixed language speech recognition systems

  2010cited by this paper
• Cross-lingual portability of MLP-based tandem features - a case study for English and Hungarian

  2008cited by this paper
• Hierarchical and parallel processing of modulation spectrum for ASR applications

  2008cited by this paper
• On the use of a multilingual neural network front-end

  2008cited by this paper
• Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition

  2007cited by this paper
• Probabilistic and Bottle-Neck Features for LVCSR of Meetings

  2007cited by this paper
• Results of the 2006 Spoken Term Detection Evaluation

  2006cited by this paper
• Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons

  2006cited by this paper
• Improved tone modeling for Mandarin broadcast news speech recognition

  2006cited by this paper
• TONE MODELING FOR SPEECH RECOGNITION

  2006cited by this paper
• Multi-resolution RASTA filtering for TANDEM-based ASR

  2005cited by this paper
• Adaptive training using simple target models [speech recognition applications]

  2005cited by this paper
• Multitask learning in connectionist robust ASR using recurrent neural networks

  2003cited by this paper
• Minimum Phone Error and I-smoothing for improved discriminative training

  2002cited by this paper
• Robust speech recognition using a voiced-unvoiced feature

  2002cited by this paper
• Language-independent and language-adaptive acoustic modeling for speech recognition

  2001cited by this paper
• Tandem connectionist feature extraction for conventional HMM systems

  2000cited by this paper
• Handbook of the International Phonetic Association: A Guide to the Use of the International Phonetic Alphabet

  2000cited by this paper
• Maximum likelihood linear transformations for HMM-based speech recognition

  1998cited by this paper
• Multitask Learning: A Knowledge-Based Source of Inductive Bias

  1993cited by this paper
• Connectionist Speech Recognition: A Hybrid Approach

  1993cited by this paper
• Phoneme recognition using time-delay neural networks

  1989cited by this paper

• Frontier Research on Low-Resource Speech Recognition Technology

  2023cites this paper
• Computational intelligence in processing of speech acoustics: a survey

  2022cites this paper
• Development of Multilingual ASR Using GlobalPhone for Less-Resourced Languages: The Case of Ethiopian Languages

  2020cites this paper
• Language-invariant Bottleneck Features from Adversarial End-to-end Acoustic Models for Low Resource Speech Recognition

  2019cites this paper
• Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings

  2019cites this paper
• Experimental research on the impact of similarity function selection on the quality of keyword spotting in speech signal

  2019cites this paper
• Language-Adversarial Transfer Learning for Low-Resource Speech Recognition

  2019cites this paper
• Adversarial Multilingual Training for Low-Resource Speech Recognition

  2018cites this paper
• Netze in der automatischen Spracherkennung-ein Paradigmenwechsel ? Neural Networks in Automatic Speech Recognition-a Paradigm Change ?

  2018cites this paper
• Sparse Subspace Modeling for Query by Example Spoken Term Detection

  2018cites this paper
• Submodular Based Unsupervised Data Selection

  2018cites this paper
• An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech

  2018influential citation
• Structured deep neural networks for speech recognition

  2018cites this paper
• Improving Attention-Based End-to-End ASR Systems with Sequence-Based Loss Functions

  2018cites this paper
• Analysis of Multilingual Sequence-to-Sequence speech recognition systems

  2018cites this paper
• Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling

  2018cites this paper
• Analysis of Multilingual Blstm Acoustic Model on Low and High Resource Languages

  2018cites this paper
• Improving Interpretability and Regularization in Deep Learning

  2018cites this paper
• Efficient methods to train multilingual bottleneck feature extractors for low resource keyword search

  2017cites this paper
• Investigate automatic speech recognition and keyword search for very low-resource language

  2017cites this paper
• Knowledge distillation across ensembles of multilingual models for low-resource languages

  2017cites this paper
• Improving Deliverable Speech-to-Text Systems with Multilingual Knowledge Transfer

  2017cites this paper
• Language independent end-to-end architecture for joint language identification and speech recognition

  2017cites this paper
• Shefce: A Cantonese-English bilingual speech corpus for pronunciation assessment

  2017cites this paper
• The 2016 RWTH Keyword Search System for Low-Resource Languages

  2017cites this paper
• Recurrent neural network language models for keyword search

  2017cites this paper
• Multi-Language Neural Network Language Models

  2016cites this paper
• Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions

  2016cites this paper
• Stimulated Deep Neural Network for Speech Recognition

  2016cites this paper
• Improvements in language and translation modeling

  2016cites this paper
• Automatic Speech Recognition Based on Neural Networks

  2016cites this paper
• Cross-lingual deep neural network based submodular unbiased data selection for low-resource keyword search

  2016cites this paper
• Rapid Update of Multilingual Deep Neural Network for Low-Resource Keyword Search

  2016cites this paper
• Multilingual region-dependent transforms

  2016cites this paper
• The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task

  2016cites this paper
• Spoken Language Technology for Under-resourced Languages , SLTU 2016 , 9-12 May 2016 , Yogyakarta , Indonesia BottleNeck Feature Extraction Structures for Multilingual Training and Porting

  2016cites this paper
• Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting

  2016cites this paper
• Scalable Recurrent Neural Network Language Models for Speech Recognition

  2015cites this paper
• An Improved Framework for Recognizing Highly Imbalanced Bilingual Code-Switched Lectures with Cross-Language Acoustic Modeling and Frame-Level Language Identification

  2015cites this paper
• Optimizing Data Selection for Automatic Speech Recognition in Low Resource Languages

  2015cites this paper
• Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages

  2015cites this paper
• Resource-dependent acoustic and language modeling for spoken keyword search

  2015cites this paper
• Improving speech recognition and keyword search for low resource languages using web data

  2015cites this paper
• A Keyword-Aware Language Modeling Approach to Spoken Keyword Search

  2015cites this paper
• Multilingual representations for low resource speech recognition and keyword search

  2015influential citation
• Structured discriminative models using deep neural-network features

  2015cites this paper
• A comparative study of BNF and DNN multilingual training on cross-lingual low-resource speech recognition

  2015influential citation
• Lattice decoding and rescoring with long-Span neural network language models

  2014cites this paper
• Data augmentation, feature combination, and multilingual neural networks to improve ASR and KWS performance for low-resource languages

  2014cites this paper
• Further investigation into multilingual training and adaptation of stacked bottle-neck neural network structure

  2014cites this paper
• Towards better keyword search performance on Malay broadcast news data

  2014cites this paper
• Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED

  2014cites this paper
• Language Independent End-to-End Architecture For Joint Language and Speech Recognition

  year unknowncites this paper