Shanqing Cai

[ ʂ a n ˥˩   t͡ɕ ʰ i ŋ ˥   t͡s ʰ ai ˥˩ ]
蔡善清

Work at Google

I am currently working as a software engineer at Google. My current and past projects at Google include:

Glyphoid

Glyphoid is an open-source parser and calculator of handwritten mathematical formulae.

Source code


More demo videos (YouTube) 🔗

Audapter

Click to enlarge
Schematic of Audapter

"Audapter", previously known as "TransShiftMex", is a MATLAB-based software package for configurable, real-time manipulation of speech signals. It is designed for research on auditory-motor interaction in speech production, but may also be of interest to certain speech signal processing applications. Audapter is currently capable of perturbing the following acoustic parameters of speech:

  • Formant frequencies (F1 and F2), in both static and time-varying ways
  • Fundamental frequency (F0)
  • Local timing, through real-time tracking and time-warping
  • Local intensity
  • Global time delay (delayed auditory feedback)
  • Global intensity
Downloads: Requirements:
  • Windows operating system
  • MATLAB
  • ASIO-compatible sound cards and ASIO driver - see manual for details

Papers

Google Scholar 🔗 PubMed 🔗 DBLP 🔗
ResearchGate 🔗

Machine Learning Speech Hearing Bionic eyes

§ Machine Learning

  • Cai S, Venugopalan S, Tomanek K, Narayanan A, Morris MR, Brenner MP (2022) Context-Aware Abbreviation Expansion Using Large Language Models. North America Chapter of ACL.
  • Cai S, Lillianfeld L, Seaver K, Green JR, Brenner MP, Nelson PQ, Sculley D A Voice-Activated Switch for Persons with Motor and Speech Impairments: Isolated-Vowel Spotting Using Neural Networks. InterSpeech 2021.
  • Smilkov D, Thorat N, Assogba Y, Yuan A, Kreeger N, Yu P, Zhang K, Cai S, Nielsen E, Soergel D, Bileschi S, Terry M, Nicholson C, Gupta SN, Sirajuddin S, Sculley D, Monga R, Corrado G, Viegas FB, Wattenberg M. Tensorflow.js: Machine learning for the web and beyond. SysML 2019.
  • Cai S, Breck E, Nielsen E, Salib M, Sculley D. (2016). TensorFlow Debugger: Debugging Dataflow Graphs for Machine Learning. Proceedings of the Reliable Machine Learning in the Wild - NIPS 2016 Workshop.
  • Breck E,, Cai S, Nielsen E, Salib M, Sculley D. (2016). What’s your ML test score? A rubric for ML production systems. Proceedings of the Reliable Machine Learning in the Wild - NIPS 2016 Workshop.

§ Speech production and its brain mechanisms

Journal papers

  • Frankford SA, Murray ESH, Masapollo M, Cai S, Tourville JA, Nieno-Castanon A, Guenther FH. (2021). The Neural Circuitry Underlying the “Rhythm Effect” in Stuttering. J. Speech Lang. Hear. Res. 64(6S):2325-2346.
  • Daliri A, Wieland EA, Cai S, Guenther FH, Chang SE. (2017). Auditory‐motor adaptation is reduced in adults who stutter but not in children who stutter. Developmental Science.
  • Sitek KR, Cai S, Beal DS, Perkell JS, Guenther FH, Ghosh SS. (2016). Decreased Cerebellar-Orbitofrontal Connectivity Correlates with Stuttering Severity: Whole-Brain Functional and Structural Connectivity Associations with Persistent Developmental Stuttering Front. Hum. Neurosci.
  • Patel R, Reilly KJ, Archibald E, Cai S, Guenther FH. (2015). Responses to Intensity-Shifted Auditory Feedback During Running Speech. J. Speech Lang. Hear. Res. Available online: 2015-10-01
  • Cai S, Tourville JA, Beal DS, Perkell JS, Ghosh SS. (2014). Diffusion Imaging of Cerebral White Matter in Persons Who Stutter: Evidence for Network-Level Anomalies. Frontiers Hum. Neurosci. 8:54.
  • Cai S, Beal DS, Ghosh SS, Guenther FH, Perkell JS. (2014). Impaired timing adjustments in response to time-varying auditory perturbation during connected speech production in persons who stutter. Brain Lang. 129:24-29.
  • Cai S, Beal DS, Ghosh SS, Tiede MK, Guenther FH, Perkell JS. (2012). Weak responses to auditory feedback perturbation during articulation in persons who stutter: Evidence for abnormal auditory-motor transformation. PLoS ONE. 7(7):e41830.
  • Cai S, Ghosh SS, Guenther FH, Perkell JS. (2011). Focal manipulations of formant trajectories reveal a role of auditory feedback in the online control of both within-syllable and between-syllable speech timing. J. Neurosci. 31(45):16483-16490.
  • Cai S, Ghosh SS, Guenther FH, Perkell JS. (2010). Adaptive auditory feedback control of the production of the formant trajectories in the Mandarin triphthong /iau/ and its patterns of generalization. J. Acoust. Soc. Am. 128(4):2033-2048.

Theses and Dissertations

  • Cai S (2012). Online Control of Articulation Based on Auditory Feedback in Normal Speech and Stuttering: Behavioral and Modeling Studies. Ph.D. dissertation, Harvard-MIT Division of Health Science and Technology, Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Cai S (2012). Adaptive auditory-motor control of the time-varying formant trajectories in vowels and its patterns of generalization. Master's thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.

Conference papers and presentations

  • Van Brenk F, Terband H, Cai S (2014) Auditory feedback perturbation in adults and children. 2014 Motor Speech Conference, Sarasota, FL, USA, Feb. 27 - Mar. 2, 2014.
  • Terband H, van Brenk H, van der Zee A, Nijssen M, Cai S (2014) Auditory feedback perturbation in children with developmental speech sound disorders. 2014 Motor Speech Conference, Sarasota, FL, USA, Feb. 27 - Mar. 2, 2014.
  • Cai S, Guenther FH (2013) Local time-warping in auditory feedback alters articulatory timing in connected multisyllabic speech containing vowels, fricatives and stops. Presented at Acoustical Soceity of America (ASA) Satellite Symposium: Neural Bases of Speech Production, San Francisco, CA, USA, December 1, 2013.
  • Cai S, Bunnell HT, Patel R. (2013). Unsupervised vocal-tract length estimation through model-based acoustic-to-articulatory inversion. To be presented at 14th Annual Conference of the International Speech Communication Association (InterSpeech 2013), Lyon, France, Aug. 25-29, 2013.
  • Wieland EA, Cai S, Ayres K, Chang S-E. (2013) Speech motor adaptation to auditory perturbation in children who do and do not stutter. 2013 Michigan Speech and Hearing Assoc. Annual Conference, Dearborn, Michigan, USA, March 21-23, 2013.
  • Cai S, Beal DS, Guenther FH, Perkell JS, Ghosh SS. (2012) FMRI resting state connectivity of the brain in stuttering. Society for Neuroscience (SfN) Annual Meeting 2012, New Orleans, LA, Oct. 13 – 17, 2012.
  • Beal DS, Segawa J, Tourville JA, Cai S, Guenther FH. (2012) Speech motor sequence learning difficulties in persistent developmental stuttering: An fMRI study. Society for Neuroscience (SfN) Annual Meeting 2012, New Orleans, LA, Oct. 13 – 17, 2012.
  • Schaefer M, McAuliffe MCM, Liss JM, Katseff S, O'Beirne GA, Cai S. (2012). Responses to manipulations in auditory feedback: The effect of aging. 2012 Motor Speech Conference, Santa Rosa, CA, USA. Feb. 29 – March 4, 2012.
  • Beal DS, Cai S, Guenther FH, Ghosh SS, Tiede MK, Perkell, JS. (2012). The relations among stuttering severity, experiences, and kinematic variability measures. 2012 Motor Speech Conference, Santa Rosa, CA, USA. Feb. 29 – March 4, 2012.
  • Cai S, Beal DS, Ghosh SS, Tiede MK, Guenther FH, Perkell JS (2011). Comparing auditory-motor interaction in static and time-varying articulation between stutterers and normal speakers. The 3rd Neurobiology of Language Conference (NLC), Annapolis, MD, Nov. 10 – 11, 2011.
  • Cai S, Beal DS, Tiede MK, Perkell JS, Guenther FH, Ghosh SS. (2011). Relating the kinematic variability of speech to MRI-based structural integrity of brain white matter in people who stutter and people with fluent speech. Society for Neuroscience (SfN) Annual Meeting 2011, Washington, DC, Nov. 12 – 16, 2011.
  • Beal DS, Cai S, Ghosh SS, Tiede MK, Perkell, JS. (2011). The Relations Among Stuttering Severity, Experiences, & Kinematic Variability Measures. American Speech, Language and Hearing Association (ASHA) Annual Convention, San Diego, CA, Nov. 17-19, 2011.
  • Beal DS, Tourville JA, Cai S, Segawa J, Guenther FH. (2011). An fMRI Study of Speech-Sequence Learning in People Who Stutter. American Speech, Language and Hearing Association (ASHA) Annual Convention, San Diego, CA, Nov. 17-19, 2011.
  • Schaefer M, McAuliffe MCM, Liss JM, O’Beirne GA, Cai S. (2011). Responses of older individuals to manipulations in auditory feedback: Preliminary findings. The 8th Asia Pacific Conference on Speech, Language and Hearing, Christchurch, Canterbury, New Zealand, Jan. 11-14, 2011.
  • Cai S, Ghosh SS, Guenther FH, Perkell JS. (2010). The role of auditory feedback in the online control of multisyllabic articulation. International Summer School on Cognitive and Physical Models of Speech Production, Speech Perception and Production-Perception Interaction 2010, Berlin, Germany, Sept. 21 – Oct. 1, 2010.
  • Cai S, Ghosh SS, Guenther FH, and Perkell JS. (2010). Coordination of the first and second formants of the Mandarin triphthong /iau/ revealed by adaptation to auditory perturbations. (Abstract) J. Acoust. Soc. Am. 127(3), 2018. The 159th Meeting of the Acoustical Society of America, Baltimore, MD, April 19 - 23, 2010.
  • Cai S, Ghosh SS, Perkell JS, Guenther FH. (2010). The role of auditory feedback in the online control of articulatory trajectories and timing in a multi-syllabic utterance. 2010 Motor Speech Conference, Savannah, GA, March 4 - 7, 2010
  • Cai S, Boucek M, Ghosh SS, Guenther FH, Perkell JS. (2008). A system for online dynamic perturbation of formant frequencies and results from perturbation of the Mandarin triphthong /iau/. In Proceedings of the 8th Intl. Seminar on Speech Production, Strasbourg, France, Dec. 8 - 12, 2008. pp. 65-68.

§ Auditory neurophysiology

Journal papers

  • Cai S, Ma W-L, Young ED. (2009). Encoding intensity in ventral cochlear nucleus neurons following acoustic trauma: implications for loudness recruitment. J. Assoc. Res. Otolaryngol. 10(1):5-22.

Theses and Dissertations

  • Cai S (2007). Intensity encoding of ventral cochlear nucleus neurons in normal and deafened cats and correlates of loudness recruitment. Master's thesis, Department of Biomedical Engineering, The Johns Hopkins University, Baltimore, MD, USA

Conference papers and presentations

  • Cai S, Ma W-L, Letham B, Young ED. (2007). Rate-intensity functions of ventral cochlear nucleus in normal and hearing-impaired cats and their possible relationships to loudness recruitment. 30th Assoc. Res. Otolaryngol. Midwinter Meeting, Denver, Colorado, Feb. 10 - 15, 2007.
  • Letham B, Ma W-L, Cai S, Young ED. (2007). Acoustic trauma induces long-term temporal correlations in DCN. 30th Assoc. Res. Otolaryngol. Midwinter Meeting, Denver, Colorado, Feb. 10 - 15, 2007.

§ Bionic eyes

  • Fu L, Cai S, Zhang H, Hu G, Zhang X. (2006). Psychophysics of reading with a limited number of pixels: Towards the rehabilitation of reading ability with visual prosthesis. Vision Res. 46:1292-1301.
  • Fu L, Zhang H, Cai S, Hu G. (2006). Chinese printed text reading performance with pixelized prosthetic vision system. (in Chinese), J. Tsinghua Univ. (Sci. & Tech.) 46(6): 858-860, 871.
  • Cai S, Fu L, Zhang H, Hu G, Liang Z. (2005). Prosthetic visual acuity in irregular phosphene arrays under two down-sampling schemes: a simulation study. In Proc. 27th Annual Intl. Conf. IEEE-EMBS, Shanghai, China, Sept. 1 - 4, 2005. Vol. 5, pp. 5523-5526.

About

Pronuncation of the name

  • The IPA of "Shanqing" is / ʂ an  tɕ ʰ i ŋ /. The spelling is based on the transliteration system of Pinyin.
  • In American English, the approximation would be "Shahn-Cheeng".

Educational Background

My NeuroTree 🔗