@inproceedings{nokey,

title = {End-to-end streaming model for low-latency speech anonymization},

author = {W. Quamer and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2024/09/waris2024slt.pdf},

year  = {2024},

date = {2024-12-02},

urldate = {2024-12-02},

booktitle = {Proc. IEEE Spoken Language Technology Workshop (SLT 2024)},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Decoupling segmental and prosodic cues of non-native speech through vector quantization},

author = {Waris Quamer, Anurag Das, Ricardo Gutierrez-Osuna

},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2023/11/decouplingProsody2023waris.pdf},

year  = {2023},

date = {2023-08-20},

urldate = {2023-08-20},

booktitle = {Proc. Interspeech},

journal = {Interspeech 2023},

keywords = {Accent conversion, Speech, Voice conversion},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{waris2022interspeech,

title = {Zero-Shot Foreign Accent Conversion without a Native Reference},

author = {W. Quamer and A. Das and J. Levis and E. Chukharev-Hudilainen and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2023/02/quamer2022interspeech.pdf},

year  = {2022},

date = {2022-09-18},

urldate = {2022-09-18},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Deep learning, Speech},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{liberatore2022icassp,

title = {Minimizing residuals for native-nonnative voice conversion in a sparse, anchor-based representation of speech},

author = {C. Liberatore and R. Gutierrez-Osuna},

year  = {2022},

date = {2022-05-22},

booktitle = {Proc. ICASSP},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chris2021ARS,

title = {An Exemplar Selection Algorithm For Native-Nonnative Voice Conversion},

author = {C. Liberatore and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2022/07/liberatore21_interspeech.pdf},

year  = {2021},

date = {2021-08-30},

urldate = {2021-08-30},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{alif2021interspeech,

title = {Effects Of Voice Type And Task On L2 Learners’ Awareness Of Pronunciation Errors},

author = {A. Silpachai and I. Rehman and T. A. Barriuso and J. Levis and E. Chukharev-Hudilainen and G. Zhao and R. Gutierrez-Osuna},

year  = {2021},

date = {2021-08-30},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{adam2021interspeech,

title = {Assessing Posterior-Based Mispronunciation Detection on Field-Collected Recordings from Child Speech Therapy Sessions},

author = {A. Hair and G. Zhao and B. Ahmed and K. J. Ballard and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2021/08/hair_interspeech_2021.pdf},

year  = {2021},

date = {2021-08-30},

booktitle = {Proc. Interspeech},

keywords = {Automatic Speech Recognition, Childhood apraxia of speech, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shaojin-2020-interspeech,

title = {Improving the Speaker Identity of Non-Parallel Many-to-Many Voice Conversion with Adversarial Speaker Recognition},

author = {S. Ding and G. Zhao and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2020/08/IS2020_shaojin_Adversarial_speaker_classifier_camera_ready.pdf},

year  = {2020},

date = {2020-10-25},

urldate = {2020-10-25},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Deep learning, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{anurag-2020-interspeech,

title = {Understanding the Effect of Voice Quality and Accent on Talker Similarity},

author = {A. Das and G. Zhao and J. Levis and E. Chukharev-Hudilainen and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2023/02/das2020interspeech.pdf},

year  = {2020},

date = {2020-10-24},

urldate = {2020-10-24},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Deep learning, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hair2020chi,

title = {Preliminary Results From a Longitudinal Study of a Tablet-Based Speech Therapy Game},

author = {A Hair and C Markoulli and P Monroe and J McKechnie and K J Ballard and B Ahmed and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2020/02/hair2020chi.pdf},

doi = {10.1145/3334480.3382886},

isbn = {978-1-4503-6819-3/20/04},

year  = {2020},

date = {2020-04-25},

booktitle = {Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing},

publisher = {ACM},

abstract = {We previously developed a tablet-based speech therapy game called Apraxia World to address barriers to treatment and increase child motivation during therapy. In this study, we examined pronunciation improvements, child engagement over time, and caregiver evaluation performance while using our game. We recruited ten children to play Apraxia World at home during two four-week treatment blocks, separated by a two-week break; nine of ten have completed the protocol at time of writing. In the treatment blocks, children’s utterances were evaluated either by caregivers or an automated pronunciation framework. Preliminary analysis suggests that children made significant therapy gains with Apraxia World, even though caregivers evaluated pronunciation leniently. We also collected a corpus of child speech for offline examination. We will conduct additional analysis once all participants complete the protocol.},

keywords = {Automatic Speech Recognition, Childhood apraxia of speech, Health, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hair2019evaluating,

title = {Evaluating Automatic Speech Recognition for Child Speech Therapy Applications},

author = {A Hair and K J Ballard and B Ahmed and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2019/08/hair2019evaluating.pdf},

doi = {10.1145/3308561.3354606},

isbn = {978-1-4503-6676-2/19/10},

year  = {2019},

date = {2019-10-28},

booktitle = {ACM SIGACCESS Conference on Computers and Accessibility},

organization = {ACM},

abstract = {Automatic speech recognition (ASR) technology can be a useful tool in mobile apps for child speech therapy, empowering children to complete their practice with limited caregiver supervision. However, little is known about the feasibility of performing ASR on mobile devices, particularly when training data is limited. In this study, we investigated the performance of two low-resource ASR systems on disordered speech from children. We compared the open-source PocketSphinx (PS) recognizer using adapted acoustic models and a custom template-matching (TM) recognizer. TM and the adapted models significantly out-perform the default PS model. On average, maximum likelihood linear regression and maximum a posteriori adaptation increased PS accuracy from 59.4% to 63.8% and 80.0%, respectively, suggesting that the models successfully captured speaker-specific word production variations. TM reached a mean accuracy of 75.8%. },

keywords = {Automatic Speech Recognition, Childhood apraxia of speech, Health, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shaojin2019-interspeech,

title = {Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion},

author = {S. Ding and Ricardo Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2019/06/ding2019interspeech.pdf},

doi = {10.21437/Interspeech.2019-1198},

year  = {2019},

date = {2019-09-15},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{guanlong2019-interspeech,

title = {Foreign Accent Conversion by Synthesizing Speech from Phonetic Posteriorgrams},

author = {G Zhao and S. Ding and Ricardo Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2019/07/zhao2019interspeech.pdf},

year  = {2019},

date = {2019-09-15},

urldate = {2019-09-15},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Deep learning, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{levis2018psslt,

title = {Golden Speaker: Learner Experience with Computer-assisted Pronunciation Practice},

author = {J. Levis and E. Chukharev-Hudilainen and R. Gutierrez-Osuna and I. Lucic and A. Silpachai and S. Sonsaat},

year  = {2018},

date = {2018-09-06},

booktitle = {Proc. Pronunciation in Second Language Learning and Teaching Conference},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ding2018interspeech2,

title = {Improving Sparse Representations in Exemplar-Based Voice Conversion with a Phoneme-Selective Objective Function},

author = {S. Ding and G Zhao and C. Liberatore and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/09/ding2018interspeech2.pdf},

doi = {10.21437/Interspeech.2018-1272},

year  = {2018},

date = {2018-09-02},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhao2018interspeech,

title = {L2-ARCTIC: A Non-Native English Speech Corpus},

author = {G Zhao and S Sonsaat and A Silpachai and I Lucic and E Chukharev-Hudilainen and J Levis and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/08/zhao2018interspeech.pdf

https://psi.engr.tamu.edu/l2-arctic-corpus/},

year  = {2018},

date = {2018-09-02},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ding2018interspeech1,

title = {Learning Structured Dictionaries for Exemplar-based Voice Conversion},

author = {S. Ding and C. Liberatore and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/09/ding2018interspeech1.pdf},

doi = {10.21437/Interspeech.2018-1295},

year  = {2018},

date = {2018-09-02},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hair2018idc,

title = {Apraxia World: A Speech Therapy Game for Children with Speech Sound Disorders},

author = {A Hair and P Monroe and B Ahmed and K J Ballard and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/04/hair2018idc.pdf},

doi = {10.1145/3202185.3202733},

isbn = {978-1-4503-5152-2/18/06},

year  = {2018},

date = {2018-06-19},

booktitle = {Proceedings of the 2018 Conference on Interaction Design and Children},

publisher = {ACM},

abstract = {This paper presents Apraxia World, a remote therapy tool for speech sound disorders that integrates speech exercises into an engaging platformer-style game. In Apraxia World, the player controls the avatar with virtual buttons/joystick, whereas speech input is associated with assets needed to advance from one level to the next. We tested performance and child preference of two strategies for delivering speech exercises: during each level, and after it. Most children indicated that doing exercises after completing each level was less disruptive and preferable to doing exercises scattered through the level. We also found that children liked having perceived control over the game (character appearance, exercise behavior). Our results indicate that (i) a familiar style of game successfully engages children, (ii) speech exercises function well when decoupled from game control, and (iii) children are willing to complete required speech exercises while playing a game they enjoy.},

keywords = {Childhood apraxia of speech, Health, Mobile computing, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liberatore2018icassp,

title = {Voice Conversion through Residual Warping in a Sparse, Anchor-Based Representation of Speech},

author = {C Liberatore and G Zhao and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/03/liberatore-icassp2018.pdf},

year  = {2018},

date = {2018-04-15},

booktitle = {Proc. ICASSP},

abstract = {In previous work we presented a Sparse, Anchor-Based Representation of speech (SABR) that uses phonemic “anchors” to represent an utterance with a set of sparse non-negative weights. SABR is speaker-independent: combining weights from a source speaker with anchors from a target speaker can be used for voice conversion. Here, we present an extension of the original SABR that significantly improves voice conversion synthesis. Namely, we take the residual signal from the SABR decomposition of the source speaker’s utterance, and warp it to the target speaker’s space using a weighted warping function learned from pairs of source-target

anchors. Using subjective and objective evaluations, we examine the performance of adding the warped residual (SABR+Res) to the original synthesis (SABR). Specifically, listeners rated SABR+Res with an average mean opinion score (MOS) of 3.6, a significant improvement compared to 2.2 MOS for SABR alone (𝑝 < 0.01) and

2.5 MOS for a baseline GMM method (𝑝 < 0.01). In an XAB speaker identity test, listeners correctly identified the identity of SABR+Res (81%) and SABR (84%) as requently as a GMM method (82%) (𝑝 = 0.70, 𝑝 = 0.35). These results indicate that adding the warped residual can dramatically improve synthesis while retaining the 

 desirable independent qualities of SABR models.},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhao2018icassp,

title = {Accent conversion using phonetic posteriorgrams},

author = {G Zhao and S Sonsaat and J Levis and E Chukharev-Hudilainen and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/03/zhao2018icassp.pdf

http://people.tamu.edu/~guanlong.zhao/icassp18_demo.html

https://psi.engr.tamu.edu/l2-arctic-corpus/

https://github.com/guanlongzhao/ppg-gmm},

year  = {2018},

date = {2018-04-15},

urldate = {2018-04-15},

booktitle = {Proc. ICASSP},

keywords = {Accent conversion, Deep learning, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{genna2018tactons,

title = {Training Behavior of Successful Tacton-Phoneme Learners},

author = {G. Angello and G. Zhao and A. B. Manam and R. Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2022/01/AngelloHaptics2018-2.pdf},

year  = {2018},

date = {2018-03-25},

booktitle = {IEEE Haptics Symposium},

keywords = {Other, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shipman2017assets,

title = {Speed-Accuracy Tradeoffs for Detecting Sign Language Content in Video Sharing Sites},

author = {F Shipman and S Duggina and C Monteiro and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/shipman2017assets.pdf},

year  = {2017},

date = {2017-11-21},

booktitle = {Proceedings of ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2017)},

pages = {185-189},

keywords = {Computer vision, Gestures, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zhao-2017-icassp,

title = {Exemplar selection methods in voice conversion},

author = {G Zhao and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/zhao2017icassp.pdf

http://people.tamu.edu/~guanlong.zhao/spring17/icassp17},

doi = {10.1109/ICASSP.2017.7953213},

year  = {2017},

date = {2017-03-05},

booktitle = {Proc. 42nd International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},

pages = {5525-5529},

keywords = {Speech, Voice conversion},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{aryal-2016-interspeech,

title = {Comparing Articulatory and Acoustic Strategies for Reducing Non-Native Accents},

author = {S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/aryal2016interspeech.pdf},

year  = {2016},

date = {2016-09-08},

booktitle = {Proc. Interspeech},

keywords = {Accent conversion, Articulatory synthesis, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liberatore2016interspeech,

title = {Generating Gestural Scores from Acoustics Through a Sparse Anchor-Based Representation of Speech},

author = {C Liberatore and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/liberatore2016interspeech.pdf},

year  = {2016},

date = {2016-09-08},

booktitle = {Proc. Interspeech},

keywords = {Articulatory synthesis, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shahin2016icassp,

title = {Classification of bisyllabic lexical stress patterns in disordered speech using deep learning},

author = {M Shahin and R Gutierrez-Osuna and B Ahmed},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/shahin2016icassp.pdf},

year  = {2016},

date = {2016-03-20},

booktitle = {Proc. International Conference on Acoustics, Speech, and Signal Processing},

keywords = {Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mckechnie-2016-motorspeech,

title = {Influence of type of feedback on effect of tablet-based delivery of intensive speech therapy in children with Childhood Apraxia of Speech},

author = {J McKechnie and K J Ballard and P McCabe and E Murray and T Lan and R Gutierrez-Osuna and B Ahmed},

year  = {2016},

date = {2016-03-03},

booktitle = {Proceedings of the Motor Speech Conference},

journal = {Motor Speech Conference},

keywords = {Childhood apraxia of speech, Games, Health, Mobile computing, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{aryal2015interspeech,

title = {Articulatory-based conversion of foreign accents with deep neural networks},

author = {S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/aryal2015interspeech.pdf},

year  = {2015},

date = {2015-09-06},

urldate = {2015-09-06},

booktitle = {Proc. Interspeech},

pages = {3385-3389},

keywords = {Accent conversion, Articulatory synthesis, Deep learning, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lan2014chiplay,

title = {Flappy Voice: An Interactive Game for Childhood Apraxia of Speech Therapy},

author = {T Lan and S Aryal and B Ahmed and K Ballard and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/lan2014chiplay.pdf},

year  = {2014},

date = {2014-10-19},

booktitle = {Proc. CHI-PLAY},

keywords = {Childhood apraxia of speech, Games, Health, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mostafa2014interspeech,

title = {A comparison of GMM-HMM and DNN-HMM based pronunciation verification techniques for use in the assessment of childhood apraxia of speech},

author = {M Shahin and B Ahmed and J McKechnie and K Ballard and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/mostafa2014interspeech.pdf},

year  = {2014},

date = {2014-09-14},

booktitle = {Proc. Interspeech},

keywords = {Childhood apraxia of speech, Health, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{jacqui2013australiaSLPconference,

title = {Tablet-based delivery of intensive speech therapy in children with Childhood Apraxia of Speech - Pilot Phase},

author = {J McKechnie and K Ballard and P McCabe and R Gutierrez-Osuna and V Karappa and A Parnandi and M Shahin and E Murray and B Ahmed},

year  = {2014},

date = {2014-05-14},

urldate = {2014-05-14},

booktitle = {Speech Pathology Australia National Conference},

keywords = {Games, Health, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{danielprocrustes2014icassp,

title = {Normalization of articulatory data through Procrustes transformations and analysis-by-synthesis},

author = {D Felps and S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/danielprocrustes2014icassp.pdf},

year  = {2014},

date = {2014-05-09},

booktitle = {Proc. 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},

pages = {3051-3055},

keywords = {Accent conversion, Articulatory synthesis, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sandeshaccentconversion2014icassp,

title = {Can voice conversion be used to reduce non-native accents},

author = {S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/sandeshaccentconversion2014icassp.pdf},

year  = {2014},

date = {2014-05-09},

booktitle = {Proc. 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},

pages = {7929-7933},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sandesh2014icassp,

title = {Accent conversion through cross-speaker articulatory synthesis},

author = {S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/sandesh2014icassp.pdf},

year  = {2014},

date = {2014-05-09},

booktitle = {Proc. 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},

pages = {7744-7748},

keywords = {Accent conversion, Articulatory synthesis, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{aryal2013interspeech,

title = {Foreign Accent Conversion through Voice Morphing},

author = {S Aryal and D Felps and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/aryal2013interspeech.pdf},

year  = {2013},

date = {2013-08-25},

booktitle = {Interspeech},

pages = {3077-3081},

keywords = {Accent conversion, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{aryal2013icassp,

title = {Articulatory inversion and synthesis: towards articulatory-based modification of speech},

author = {S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/aryal2013icassp.pdf},

year  = {2013},

date = {2013-02-28},

booktitle = {38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},

pages = {7952-7956},

keywords = {Articulatory inversion, Articulatory synthesis, Speech},

pubstate = {published},

tppubtype = {inproceedings}

}