CoChat
Sign Up
Cited by 4Voice and Speech DisordersSpeech Recognition and SynthesisSpeech and Audio Processing

Detecting and Analysing Spontaneous Oral Cancer Speech in the Wild

Open access
Halpern, Bence Mark, Son, Rob van, Brekel, Michiel van den, Scharenborg, Odette·2020·Interspeech 2020
DOI 10.21437/interspeech.2020-1598
Open this paper in CoChat — free account

Abstract

Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21437/interspeech.2020-1598

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Current speech recognition systems are poorly equipped to process the speech variance and impaired speech intelligibility due to, e.g., oral cancer, cleft lip and palate, or stroke survivors.

    “Current speech recognition systems are poorly equipped to process the speech variance and impaired speech intelligibility due to, e.g., oral cancer (Halpern et al. 2020), cleft lip and palate (Schuster et al. 2006) or stroke survivors (Jacks et al. 2019).”

    From “Alexa, who am I?”: Voice Assistants and Hermeneutic Lemniscate as the Technologically Mediated Sense-Making (2021) · cites this paper as Halpern et al. 2020

    The Introduction (p. 1) says oral cancer survivors can have impaired speech intelligibility and describes how treatment alters their articulation. But the paper studies detection of oral cancer speech, not whether current speech recognition systems are poorly equipped to process it. Cleft lip and palate and stroke survivors are attributed to separate citations in the citing sentence. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 35

  1. [1][1] Kevin D Shield, Jacques Ferlay, Ahmedin Jemal, Rengaswamy Sankaranarayanan, Anil K Chaturvedi, Freddie Bray, and Isabelle Soerjomataram, 'The global incidence of lip, oral cavity, and pharyngeal cancers by subsite in 2012,' CA: a cancer journal for clinicians , vol. 67, no. 1, pp. 51-64, 2017. -
  2. [3][3] Elizabeth C Ward and Corina J van As-Brooks, Head and neck cancer: treatment, rehabilitation, and outcomes. Chapter 5: Speech and Swallowing Following Oral, Oropharyngeal, and Nasopharyngeal Cancer , Plural Publishing, 2014. -
  3. [4][4] Jeri A Logemann, Barbara Roa Pauloski, Alfred W Rademaker, and Laura A Colangelo, 'Speech and swallowing rehabilitation for head and neck cancer patients,' Oncology , vol. 11, no. 5, 1997. -
  4. [5][5] KDR Kappert, MJA van Alphen, LE Smeele, AJM Balm, and F van der Heijden, 'Quantification of tongue mobility impairment using optical tracking in patients after receiving primary surgery or chemoradiation,' PloS one , vol. 14, no. 8, 2019. -
  5. [6][6] Tim Bressmann, Hannah Jacobs, Janette Quintero, and Jonathan C Irish, 'Speech outcomes for partial glossectomy surgery: Measures of speech articulation and listener perception indicateurs de 7. la parole pour une glossectomie partielle: Mesures de larticulation de la parole et de la perception des auditeurs,' Head and Neck Cancer , vol. 33, no. 4, pp. 204, 2009. -
  6. [7][7] Tim Bressmann, Robert Sader, Tara L Whitehill, and Nabil Samman, 'Consonant intelligibility and tongue motility in patients with partial glossectomy,' Journal of Oral and Maxillofacial Surgery , vol. 62, no. 3, pp. 298-303, 2004. -
  7. [8][8] Juha-Pertti Laaksonen, Jana Rieger, Jeffrey Harris, and Hadi Seikaly, 'A longitudinal acoustic study of the effects of the radial forearm free flap reconstruction on sibilants produced by tongue cancer patients,' Clinical linguistics & phonetics , vol. 25, no. 4, pp. 253-264, 2011. -
  8. [9][9] Juha-Pertti Laaksonen, Jana Rieger, Risto-Pekka Happonen, Jeffrey Harris, and Hadi Seikaly, 'Speech after radial forearm free flap reconstruction of the tongue: a longitudinal acoustic study of vowel and diphthong sounds,' Clinical linguistics & phonetics , vol. 24, no. 1, pp. 41-54, 2010. -
  9. [10][10] Marieke J De Bruijn, Louis Ten Bosch, Dirk J Kuik, Hugo Quen´ e, Johannes A Langendijk, C Ren´ e Leemans, and Irma M Verdonckde Leeuw, 'Objective acoustic-phonetic speech analysis in patients treated for oral or oropharyngeal cancer,' Folia Phoniatrica et Logopaedica , vol. 61, no. 3, pp. 180-187, 2009. -
  10. [11][11] Calvin Thomas, Vlado Keselj, Nick Cercone, Kenneth Rockwood, and Elissa Asp, 'Automatic detection and rating of dementia of alzheimer type through lexical analysis of spontaneous speech,' in IEEE International Conference Mechatronics and Automation, 2005 . IEEE, 2005, vol. 3, pp. 1569-1574. -
  11. [12][12] M. Windrich, A. Maier, R. Kohler, E. Nth, E. Nkenke, U. Eysholdt, and M. Schuster, 'Automatic quantification of speech intelligibility of adults with oral squamous cell carcinoma,' Folia Phoniatrica et Logopaedica , vol. 60, no. 3, pp. 151-6, 2009. -
  12. [13][13] Andreas Maier, Elmar N¨ oth, Anton Batliner, Emeka Nkenke, and Maria Schuster, 'Fully automatic assessment of speech of children with cleft lip and palate,' Informatica , vol. 30, no. 4, 2006. -
  13. [14][14] Florian Eyben and Bj¨ orn Schuller, 'opensmile:) the munich opensource large-scale multimedia feature extractor,' ACM SIGMultimedia Records , vol. 6, no. 4, pp. 4-13, 2015. -
  14. [15][15] Daniel Povey, Arnab Ghoshal, Gilles Boulianne, Lukas Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlicek, Yanmin Qian, Petr Schwarz, et al., 'The kaldi speech recognition toolkit,' in IEEE 2011 workshop on automatic speech recognition and understanding . IEEE Signal Processing Society, 2011. -
  15. [16][16] Brian McFee, Colin Raffel, Dawen Liang, Daniel PW Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto, 'librosa: Audio and music signal analysis in python,' in Proceedings of the 14th python in science conference , 2015, vol. 8. -
  16. [17][17] Philipp Klumpp, Julian Fritsch, and Elmar N¨ oth, 'Ann-based alzheimer's disease classification from bag of words,' in Speech Communication; 13th ITG-Symposium . VDE, 2018, pp. 1-4. -
  17. [18][18] Alireza A Dibazar, S Narayanan, and Theodore W Berger, 'Feature analysis for automatic detection of pathological speech,' in Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society][Engineering in Medicine and Biology . IEEE, 2002, vol. 1, pp. 182-183. -
  18. [19][19] Tobias Bocklet, Andreas Maier, Josef G Bauer, Felix Burkhardt, and Elmar Noth, 'Age and gender recognition for telephone applications based on gmm supervectors and support vector machines,' in ICASSP . IEEE, 2008, pp. 1605-1608. -
  19. [20][20] Cassia Valentini-Botinhao, Sabine Degenkolb-Weyers, Andreas Maier, Elmar N¨ oth, Ulrich Eysholdt, and Tobias Bocklet, 'Automatic detection of sigmatism in children,' in Third Workshop on Child, Computer and Interaction , 2012. -
  20. [21][21] Arsha Nagrani, Joon Son Chung, and Andrew Zisserman, 'Voxceleb: A large-scale speaker identification dataset,' in Interspeech , 2017, pp. 2616-2620. -
  21. [24][24] Kristine Tanner, Nelson Roy, Andrea Ash, and Eugene H. Buder, 'Spectral moments of the long-term average spectrum: Sensitive indices of voice change after therapy?,' Journal of Voice , 2005. -
  22. [25][25] Gunnar Fant, 'The source filter concept in voice production,' STL-QPSR , vol. 1, no. 1981, pp. 21-37, 1981. -
  23. [26][26] Hynek Hermansky, 'Perceptual linear predictive (plp) analysis of speech,' the Journal of the Acoustical Society of America , vol. 87, no. 4, pp. 1738-1752, 1990. -
  24. [27][27] Pegah Ghahremani, Bagher BabaAli, Daniel Povey, Korbinian Riedhammer, Jan Trmal, and Sanjeev Khudanpur, 'A pitch extraction algorithm tuned for automatic speech recognition,' in ICASSP . IEEE, 2014, pp. 2494-2498. -
  25. [28][28] Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur, 'Librispeech: an asr corpus based on public domain audio books,' in ICASSP . IEEE, 2015, pp. 5206-5210. -
  26. [29][29] Guanlong Zhao, Shaojin Ding, and Ricardo Gutierrez-Osuna, 'Foreign accent conversion by synthesizing speech from phonetic posteriorgrams,' in Interspeech , 2019, pp. 2843-2847. -
  27. [30][30] Robert Tibshirani, 'Regression shrinkage and selection via the lasso,' Journal of the Royal Statistical Society: Series B (Methodological) , vol. 58, no. 1, pp. 267-288, 1996. -
  28. [31][31] Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake VanderPlas, Arnaud Joly, Brian Holt, and Ga¨ el Varoquaux, 'API design for machine learning software: experiences from the scikit-learn project,' in ECML PKDD Workshop: Languages for Data Mining and Machine Learning , 2013, pp. 108122. -
  29. [32][32] Fisher Yu, Vladlen Koltun, and Thomas A. Funkhouser, 'Dilated residual networks,' CoRR , vol. abs/1705.09914, 2017. - · arXiv
  30. [33][33] Bence Mark Halpern, Finnian Kelly, Rob Van Son, and Anil Alexander, 'Residual networks for resisting noise: analysis of an embeddings-based spoofing countermeasure,' in Odyssey The Speaker and Language Recognition Workshop , 2020. -
  31. [34][34] Cheng-I Lai, Nanxin Chen, Jes´ us Villalba, and Najim Dehak, 'ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual Networks,' in Interspeech , 2019, pp. 1013-1017. -
  32. [35][35] Jonathan Shen, Ruoming Pang, Ron J Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, Rj Skerrv-Ryan, et al., 'Natural tts synthesis by conditioning wavenet on mel spectrogram predictions,' in ICASSP . IEEE, 2018, pp. 4779-4783. -
  33. [37][37] Diederik P. Kingma and Jimmy Ba, 'Adam: A method for stochastic optimization,' in 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings , Yoshua Bengio and Yann LeCun, Eds., 2015. -
  34. [38][38] Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra, 'GradCAM: Visual Explanations from Deep Networks via GradientBased Localization,' in Proceedings of the IEEE International Conference on Computer Vision , 2017. -
  35. [39][39] Peter Ladefoged and Sandra Ferrari DIsner, Vowels and consonants , Wiley & Blackwell, 2012.

Cited by

Sorted by citations

Authors
Halpern, B. M., Son, R. V., Brekel, M. V. D., & Scharenborg, O.
Affiliations
  • The Netherlands Cancer Institute (NL)
  • Delft University of Technology (NL)
ORCID
Venue
Interspeech 2020
Publisher
ISCA
Published
2020-10-25
Pages
4826-4830
ISSN
2308-457X (ISSN-L)
DOI
10.21437/interspeech.2020-1598
OpenAlex
W3046013785
Cited by
4
References
0
Citations by year
2023: 2 · 2022: 1 · 2021: 1
FWCI
4.69
Type
conference paper
Language
en
Open access
Licence
other-oa
Locations
  • Interspeech (USB) (publishedVersion)
  • UvA-DARE (University of Amsterdam) (publishedVersion, other-oa)
  • arXiv (Cornell University) (submittedVersion)
  • Data Archiving and Networked Services (DANS) (submittedVersion)
  • Pure Amsterdam UMC (submittedVersion)
  • Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
  • arXiv (Cornell University)
Funders
European Commission (766287, HORIZON2020)
Topics
  • Health Sciences › Medicine › Physiology › Voice and Speech Disorders
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
Keywords
spontaneous speech, speech detection, sibilants, stop consonants, explainable machine learning, speech dataset

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review