György Szaszák

According to our database1, György Szaszák authored at least 54 papers between 2004 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
Automatic Assessment Of Spoken English Proficiency Based on Multimodal and Multitask Transformers.
Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, 2023

2021
Deep Learning Methods in Speaker Recognition: A Review.
Period. Polytech. Electr. Eng. Comput. Sci., 2021

2020
A low latency sequential model and its user-focused evaluation for automatic punctuation of ASR closed captions.
Comput. Speech Lang., 2020

Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR.
CoRR, 2020

On the Effectiveness of Neural Text Generation Based Data Augmentation for Recognition of Morphologically Rich Speech.
Proceedings of the Text, Speech, and Dialogue, 2020

Using ASR Posterior Probability and Acoustic Features for Voice Disorder Classification.
Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications, 2020

Improving Real-time Recognition of Morphologically Rich Speech with Transformer Language Model.
Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications, 2020

2019
On the Effects of Automatic Transcription and Segmentation Errors in Hungarian Spoken Language Processing.
Period. Polytech. Electr. Eng. Comput. Sci., 2019

Investigation on N-Gram Approximated RNNLMs for Recognition of Morphologically Rich Speech.
Proceedings of the Statistical Language and Speech Processing, 2019

Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian.
Proceedings of the 4th Workshop on Representation Learning for NLP, 2019

Assessing the Semantic Space Bias Caused by ASR Error Propagation and its Effect on Spoken Document Summarization.
Proceedings of the Interspeech 2019, 2019

Leveraging a Character, Word and Prosody Triplet for an ASR Error Robust and Agglutination Friendly Punctuation Approach.
Proceedings of the Interspeech 2019, 2019

Artificial Neural Network and SVM based Voice Disorder Classification.
Proceedings of the 10th IEEE International Conference on Cognitive Infocommunications, 2019

N-gram Approximation of LSTM Recurrent Language Models for Single-pass Recognition of Hungarian Call Center Conversations.
Proceedings of the 10th IEEE International Conference on Cognitive Infocommunications, 2019

2018
Prosodic stress detection for fixed stress languages using formal atom decomposition and a statistical hidden Markov hybrid.
Speech Commun., 2018

User-centric Evaluation of Automatic Punctuation in ASR Closed Captioning.
Proceedings of the Interspeech 2018, 2018

Joint Word- and Character-level Embedding CNN-RNN Models for Punctuation Restoration.
Proceedings of the 9th IEEE International Conference on Cognitive Infocommunications, 2018

A semantic space approach for automatic summarization of documents.
Proceedings of the 9th IEEE International Conference on Cognitive Infocommunications, 2018

2017
Low Latency MaxEnt- and RNN-Based Word Sequence Models for Punctuation Restoration of Closed Caption Data.
Proceedings of the Statistical Language and Speech Processing, 2017

Semi-Supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control.
Proceedings of the Interspeech 2017, 2017

A Phonological Phrase Sequence Modelling Approach for Resource Efficient and Robust Real-Time Punctuation Recovery.
Proceedings of the Interspeech 2017, 2017

Á bilingual comparison of MaxEnt-and RNN-based punctuation restoration in speech transcripts.
Proceedings of the 8th IEEE International Conference on Cognitive Infocommunications, 2017

Assessment of pathological speech prosody based on automatic stress detection and phrasing approaches.
Proceedings of the 8th IEEE International Conference on Cognitive Infocommunications, 2017

A prosody inspired RNN approach for punctuation of machine produced speech transcripts to improve human readability.
Proceedings of the 8th IEEE International Conference on Cognitive Infocommunications, 2017

A context-aware speech recognition and understanding system for air traffic control domain.
Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016
Ensemble Deep Neural Network Based Waveform-Driven Stress Model for Speech Synthesis.
Proceedings of the Speech and Computer - 18th International Conference, 2016

Combining Atom Decomposition of the F0 Track and HMM-based Phonological Phrase Modelling for Robust Stress Detection in Speech.
Proceedings of the Speech and Computer - 18th International Conference, 2016

Design of a Speech Corpus for Research on Cross-Lingual Prosody Transfer.
Proceedings of the Speech and Computer - 18th International Conference, 2016

Automatic Summarization of Highly Spontaneous Speech.
Proceedings of the Speech and Computer - 18th International Conference, 2016

Estimating the Sincerity of Apologies in Speech by DNN Rank Learning and Prosodic Analysis.
Proceedings of the Interspeech 2016, 2016

Summarization of Spontaneous Speech using Automatic Speech Recognition and a Speech Prosody based Tokenizer.
Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2016) - Volume 1: KDIR, Porto - Portugal, November 9, 2016

Atom decomposition based stress detection and automatic phrasing of speech.
Proceedings of the 7th IEEE International Conference on Cognitive Infocommunications, 2016

2015
Toward Exploring the Role of Disfluencies from an Acoustic Point of View: A New Aspect of (Dis)continuous Speech Prosody Modelling.
Proceedings of the Text, Speech, and Dialogue - 18th International Conference, 2015

Automatic Close Captioning for Live Hungarian Television Broadcast Speech: A Fast and Resource-Efficient Approach.
Proceedings of the Speech and Computer - 17th International Conference, 2015

Using automatic stress extraction from audio for improved prosody modelling in speech synthesis.
Proceedings of the INTERSPEECH 2015, 2015

2014
Combining NLP techniques and acoustic analysis for semantic focus detection in speech.
Proceedings of the 5th IEEE Conference on Cognitive Infocommunications, 2014

2013
Using phonological phrase segmentation to improve automatic keyword spotting for the highly agglutinating Hungarian language.
Proceedings of the INTERSPEECH 2013, 2013

Evaluating intra- and crosslingual adaptation for non-native speech recognition in a bilingual environment.
Proceedings of the IEEE 4th International Conference on Cognitive Infocommunications, 2013

Automatic phrase segmentation and clustering in spontaneous speech.
Proceedings of the IEEE 4th International Conference on Cognitive Infocommunications, 2013

2012
Exploiting Prosody for Syntactic Analysis in Automatic Speech Understanding.
J. Lang. Model., 2012

Unsupervised Clustering of Prosodic Patterns in Spontaneous Speech.
Proceedings of the Text, Speech and Dialogue - 15th International Conference, 2012

Automatic prosodic and syntactic analysis from speech in cognitive infocommunication.
Proceedings of the IEEE 3rd International Conference on Cognitive Infocommunications, 2012

2011
Automatic Intonation Recognition for the Prosodic Assessment of Language-Impaired Children.
IEEE Trans. Speech Audio Process., 2011

Analysing the Correspondence Between Automatic Prosodic Segmentation and Syntactic Structure.
Proceedings of the INTERSPEECH 2011, 2011

2010
Using prosody to improve automatic speech recognition.
Speech Commun., 2010

2009
A szupraszegmentális jellemzők szerepe és felhasználása a gépi beszédfelismerésben
PhD thesis, 2009

Automatic intonation classification for speech training systems.
Proceedings of the INTERSPEECH 2009, 2009

2008
Using prosody for the improvement of ASR - sentence modality recognition.
Proceedings of the INTERSPEECH 2008, 2008

2007
Speech Recognition Supported by Prosodic Information for Fixed Stress Languages.
Proceedings of the Text, Speech and Dialogue, 10th International Conference, 2007

Using Prosody in Fixed Stress Languages for Improvement of Speech Recognition.
Proceedings of the Verbal and Nonverbal Communication Behaviours, 2007

2006
Prosodic Cues for Automatic Phrase Boundary Detection in ASR.
Proceedings of the Text, Speech and Dialogue, 9th International Conference, 2006

2005
Automatic Segmentation of Continuous Speech on Word Level Based on Supra-segmental Features.
Int. J. Speech Technol., 2005

2004
Examination of Pronunciation Variation from Hand-Labelled Corpora.
Proceedings of the Text, Speech and Dialogue, 7th International Conference, 2004

The COST 278 MASPER Initiative - Crosslingual Speech Recognition with Large Telephone Databases.
Proceedings of the Fourth International Conference on Language Resources and Evaluation, 2004


  Loading...