Personal information

Other IDs

Scopus Author ID: 35105904000

Keywords

audio processing, deepfake detection, speech synthesis, deep learning, artificial intelligence

Countries

Romania

Activities

Collapse all

Employment (1)

Universitatea Tehnică din Cluj-Napoca: Cluj Napoca, Cluj, RO

2024-02-01 to present | Professor (Communications Department)
Employment
Source: Self-asserted source
Adriana Stan

Education and qualifications (1)

Universitatea Tehnica Cluj Napoca: Cluj Napoca, Cluj, RO

2008-10-01 to 2011-09-16 | PhD (Communications Department)
Education
Source: Self-asserted source
Adriana Stan

Works (41)

An analysis of large speech models-based representations for speech emotion recognition

ArXiv
2023 | Journal article
WOSUID: PPRN:85929482
Contributors: Stanea, Adrian Bogdan; Striletchi, Vlad; Striletchi, Cosmin; Stan, Adriana
Source: check_circle
Web of Science Researcher Profile Sync
grade
Preferred source (of 3)‎

Gamification-Based Tools Embedded in the Helios Educational Platform

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation
2022 | Journal article
DOI: 10.1007/978-3-031-04819-7_46
WOSUID: WOS:000873540000046
Contributors: Striletchi, Cosmin; Stan, Adriana Cornelia; Jecan, Eusebiu
Source: check_circle
Web of Science Researcher Profile Sync

RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information

Natural Language Processing
2022 | Journal article
DOI: 10.1017/S1351324922000419
WOSUID: WOS:000844868900001
Contributors: Lorincz, Beata; Irimia, Elena; Stan, Adriana; Mititelu, Verginica Barbu
Source: check_circle
Web of Science Researcher Profile Sync

Residual Information in Deep Speaker Embedding Architectures

Mathematics
2022-10-23 | Journal article | Author
DOI: 10.3390/math10213927
Part of ISSN: 2227-7390
Contributors: Adriana Stan
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 3)‎

The ZevoMOS entry to VoiceMOS Challenge 2022

Interspeech 2022
2022-09-18 | Conference paper
DOI: 10.21437/INTERSPEECH.2022-105
WOSUID: WOS:000900724504140
WOSUID: PPRN:12415246
Contributors: Adriana Stan; Adriana Stan
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

FlexLip: A Controllable Text-to-Lip System

Sensors
2022-05-28 | Journal article
DOI: 10.3390/s22114104
Contributors: Dan Oneață; Beáta Lőrincz; Adriana Stan; Horia Cucu
Source: check_circle
Crossref
grade
Preferred source (of 3)‎

An analysis of the data efficiency in Tacotron2 speech synthesis system

International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
2021 | Conference paper
DOI: 10.1109/SPED53181.2021.9587411
WOSUID: WOS:000786794700031
Contributors: Saracu, Georgiana; Stan, Adriana
Source: check_circle
Web of Science Researcher Profile Sync

An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis

Procedia Computer Science
2021 | Journal article
DOI: 10.1016/J.PROCS.2021.08.078
WOSUID: WOS:000720289000077
Contributors: Lorincz, Beata; Stan, Adriana; Giurgiu, Mircea
Source: check_circle
Web of Science Researcher Profile Sync
grade
Preferred source (of 3)‎

Speaker disentanglement in video-to-speech conversion

European Signal Processing Conference
2021 | Conference paper
WOSUID: WOS:000764066600010
Contributors: Oneata, Dan; Stan, Adriana; Cucu, Horia
Source: check_circle
Web of Science Researcher Profile Sync
grade
Preferred source (of 3)‎

Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis

European Signal Processing Conference
2021 | Conference paper
WOSUID: WOS:000764066600006
Contributors: Lorincz, Beata; Stan, Adriana; Giurgiu, Mircea
Source: check_circle
Web of Science Researcher Profile Sync
grade
Preferred source (of 3)‎

The MARA corpus: Expressivity in end-to-end TTS systems using synthesised speech data

International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
2021 | Conference paper
DOI: 10.1109/SPED53181.2021.9587438
WOSUID: WOS:000786794700016
Contributors: Stan, Adriana; Lorincz, Beata; Nutu, Maria; Giurgiu, Mircea
Source: check_circle
Web of Science Researcher Profile Sync

Generating the Voice of the Interactive Virtual Assistant

Virtual Assistant [Working Title]
2021-02-10 | Book chapter
DOI: 10.5772/intechopen.95510
Source: Self-asserted source
Adriana Stan

An Evaluation of Word-Level Confidence Estimation for End-to-End Automatic Speech Recognition

2021 IEEE Spoken Language Technology Workshop (SLT)
2021-01-19 | Conference paper
DOI: 10.1109/SLT48900.2021.9383570
EID:

2-s2.0-85103971650

ISBN: 9781728170664
WOSUID: PPRN:11395588
WOSUID: WOS:000663633300036
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

Designing a Synthesized Content Feed System for Community Radio

Proceedings of the 11th Nordic Conference on Human-Computer Interaction: Shaping Experiences, Shaping Society
2020-10-25 | Conference paper
DOI: 10.1145/3419249.3420177
ISBN: 9781450375795
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

RECOApy: Data Recording, Pre-Processing and Phonetic Transcription for End-to-End Speech-Based Applications

Interspeech 2020
2020-10-25 | Conference paper
DOI: 10.21437/INTERSPEECH.2020-1184
WOSUID: WOS:000833594100123
EID:

2-s2.0-85098144702

Part of ISSN: 19909772 2308457X
WOSUID: PPRN:13146507
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

An Evaluation of Postfiltering for Deep Learning Based Speech Synthesis with Limited Data

2020 IEEE 10th International Conference on Intelligent Systems (IS)
2020-08 | Conference paper
DOI: 10.1109/is48319.2020.9199932
ISBN: 9781728154565
Source: Self-asserted source
Adriana Stan

Input Encoding for Sequence-to-Sequence Learning of Romanian Grapheme-to-Phoneme Conversion

2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
2019-10 | Conference paper
DOI: 10.1109/sped.2019.8906639
ISBN: 9781728109848
Source: Self-asserted source
Adriana Stan

Romanian Part of Speech Tagging using LSTM Networks

2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP)
2019-09 | Conference paper
DOI: 10.1109/iccp48234.2019.8959730
ISBN: 9781728149141
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

All Together Now: The Living Audio Dataset

Interspeech 2019
2019-09-15 | Conference paper
DOI: 10.21437/interspeech.2019-2448
Source: Self-asserted source
Adriana Stan

A COMPARISON BETWEEN TRADITIONAL MACHINE LEARNING APPROACHES AND DEEP NEURAL NETWORKS FOR TEXT PROCESSING IN ROMANIAN

Proceedings of the International Conference Linguistic Resources and Tools for Processing the Romanian Language
2018 | Journal article
WOSUID: WOS:000610358400004
Contributors: Stan, Adriana; Giurgiu, Mircea
Source: check_circle
Web of Science Researcher Profile Sync

The Role of Speech-To-Text Systems in Improving Communication in Laryngectomized Patients in Romania

Proceedings of National Ent, Head and Neck Surgery Conference
2018 | Journal article
WOSUID: WOS:000467803000097
Contributors: Tiple, Cristina; Dinescu, Florina Veronica; Matu, Silviu; Muresan, Rodica; Soflau, Radu; Giurgiu, Mircea; Stan, Adriana; David, Daniel; Cosgarea, Marcel; Vesa, Stefan et al.
Source: check_circle
Web of Science Researcher Profile Sync

MaRePhoR - An Open Access Machine-Readable Phonetic Dictionary for Romanian

International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
2017 | Conference paper
WOSUID: WOS:000425849600010
Contributors: Tema, Stefan-Adrian; Stan, Adriana; Pura, Mihai-Lica; Barsan, Traian
Source: check_circle
Web of Science Researcher Profile Sync

The SWARA speech corpus: A large parallel Romanian read speech dataset

2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
2017-07 | Conference paper
DOI: 10.1109/sped.2017.7990428
ISBN: 9781509064977
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

Blind speech segmentation using spectrogram image-based features and Mel cepstral coefficients

2016 IEEE Spoken Language Technology Workshop (SLT)
2016-12 | Conference paper
DOI: 10.1109/slt.2016.7846324
ISBN: 9781509049035
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

Improving sentence-level alignment of speech with imperfect transcripts using utterance concatenation and VAD

2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing (ICCP)
2016-09 | Conference paper
DOI: 10.1109/iccp.2016.7737141
ISBN: 9781509038992
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

ALISA: An automatic lightly supervised speech segmentation and alignment tool

Computer Speech & Language
2016-01 | Journal article
DOI: 10.1016/j.csl.2015.06.006
Contributors: A. Stan; Y. Mamiya; J. Yamagishi; P. Bell; O. Watts; R.A.J. Clark; S. King
Source: check_circle
Crossref
grade
Preferred source (of 2)‎

Voice-Related Quality of Life Results in Laryngectomies with Today's Speech Options and Expectations from the Next Generation of Vocal Assistive Technologies

2015 E-Health and Bioengineering Conference (Ehb)
2015 | Journal article
WOSUID:

WOS:000380397900125
Contributors: Tiple, Cristina; Matu, Silviu; Dinescu, Florina Veronica; Muresan, Rodica; Soflau, Radu; Drugan, Tudor; Giurgiu, Mircea; Stan, Adriana; David, Daniel; Chirila, Magdalena et al.
Source: Self-asserted source
Adriana Stan via ResearcherID

Phonetic segmentation of speech using STEP and t-SNE

2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
2015-10 | Conference paper
DOI: 10.1109/sped.2015.7343105
ISBN: 9781467375603
Source: Self-asserted source
Adriana Stan

RSS-TOBI - A Prosodically Enhanced Romanian Speech Corpus

Lrec 2014 - Ninth International Conference on Language Resources and Evaluation
2014 | Journal article
WOSUID:

WOS:000355611001158
Contributors: Boros, Tiberiu; Stan, Adriana; Watts, Oliver; Dumitrescu, Stefan Daniel
Source: Self-asserted source
Adriana Stan via ResearcherID
grade
Preferred source (of 3)‎

An approach to lexical stress detection from transcribed continuous speech using acoustic features

2014 22nd Telecommunications Forum Telfor (TELFOR)
2014-11 | Conference paper
DOI: 10.1109/telfor.2014.7034462
ISBN: 9781479961917
ISBN: 9781479961900
Source: Self-asserted source
Adriana Stan

Neural net word representations for phrase-break prediction without a part of speech tagger

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2014-05 | Conference paper
DOI: 10.1109/ICASSP.2014.6854070
WOSUID:

WOS:000343655302127

EID:

2-s2.0-84905251790

Part of ISSN: 15206149
ISBN: 9781479928934
Source: Self-asserted source
Adriana Stan
grade
Preferred source (of 2)‎

Evaluation of Sentiment Polarity Prediction using a Dimensional and a Categorical Approach

2013 7th Conference on Speech Technology and Human - Computer Dialogue (Sped)
2013 | Journal article
WOSUID:

WOS:000330672700002
Contributors: Muresan, Ioana; Stan, Adriana; Giurgiu, Mircea; Potolea, Rodica
Source: Self-asserted source
Adriana Stan via ResearcherID

Lightly Supervised Discriminative Training of Grapheme Models for Improved Sentence-level Alignment of Speech and Text Data

14th Annual Conference of the International Speech Communication Association (Interspeech 2013), Vols 1-5
2013 | Book chapter
WOSUID:

WOS:000395050000320
Contributors: Stan, Adriana; Bell, Peter; Yamagishi, Junichi; King, Simon
Source: Self-asserted source
Adriana Stan via ResearcherID
grade
Preferred source (of 3)‎

LIGHTLY SUPERVISED GMM VAD TO USE AUDIOBOOK FOR SPEECH SYNTHESISER

2013 Ieee International Conference on Acoustics, Speech and Signal Processing
2013 | Book chapter
WOSUID:

WOS:000329611508030
Contributors: Mamiya, Yoshitaka; Yamagishi, Junichi; Watts, Oliver; Clark, Robert A. J.; King, Simon; Stan, Adriana; Ieee,
Source: Self-asserted source
Adriana Stan via ResearcherID

TUNDRA: A Multilingual Corpus of Found Data for TTS Research Created with Light Supervision

14th Annual Conference of the International Speech Communication Association (Interspeech 2013), Vols 1-5
2013 | Book chapter
WOSUID:

WOS:000395050001004
Contributors: Stan, A.; Watts, O.; Mamiya, Y.; Giurgiu, M.; Clarke, R. A. J.; Yamagishi, J.; King, S.
Source: Self-asserted source
Adriana Stan via ResearcherID
grade
Preferred source (of 3)‎

A GRAPHEME-BASED METHOD FOR AUTOMATIC ALIGNMENT OF SPEECH AND TEXT DATA

2012 Ieee Workshop on Spoken Language Technology (Slt 2012)
2012 | Journal article
WOSUID:

WOS:000317182800050
Contributors: Stan, Adriana; Bell, Peter; King, Simon; Ieee,
Source: Self-asserted source
Adriana Stan via ResearcherID

A Superpositional Model Applied to F0 Parameterization using DCT for Text-to-Speech Synthesis

2011 6th Conference on Speech Technology and Human-Computer Dialogue (Sped)
2011 | Journal article
WOSUID:

WOS:000376618200010
Contributors: Stan, Adriana; Giurgiu, Mircea
Source: Self-asserted source
Adriana Stan via ResearcherID

Interactive Intonation Optimisation Using CMA-ES and DCT Parameterisation of the F0 Contour for Speech Synthesis

Nature Inspired Cooperative Strategies for Optimization
2011 | Book chapter
WOSUID:

WOS:000307523400004
Contributors: Stan, Adriana; Pop, Florin-Claudiu; Cremene, Marcel; Giurgiu, Mircea; Pallez, Denis
Source: Self-asserted source
Adriana Stan via ResearcherID

The Romanian speech synthesis (RSS) corpus: Building a high quality HMM-based speech synthesis system using a high sampling rate

Speech Communication
2011 | Journal article
DOI: 10.1016/j.specom.2010.12.002
WOSUID:

WOS:000287561300013
Contributors: Stan, Adriana; Yamagishi, Junichi; King, Simon; Aylett, Matthew
Source: Self-asserted source
Adriana Stan via ResearcherID

Romanian language statistics and resources for text-to-speech systems

2010 9th International Symposium on Electronics and Telecommunications (Isetc)
2010 | Journal article
DOI: 10.1109/isetc.2010.5679318
WOSUID:

WOS:000296356700082
Contributors: Stan, Adriana; Giurgiu, Mircea; Ieee,
Source: Self-asserted source
Adriana Stan via ResearcherID
grade
Preferred source (of 3)‎

LINEAR INTERPOLATION OF SPECTROTEMPORAL EXCITATION PATTERN REPRESENTATIONSFOR AUTOMATIC SPEECH RECOGNITION IN THE PRESENCE OF NOISE

From Speech Processing to Spoken Language Technology
2009 | Book
WOSUID:

WOS:000280141300019
Contributors: Stan, Adriana
Source: Self-asserted source
Adriana Stan via ResearcherID
grade
Preferred source (of 3)‎

Peer review (1 review for 1 publication/grant)

Review activity for Mathematics. (1)
How many people are using ORCID?