1 |
Automatic extraction of speech rhythm descriptors for speech intelligibility assessment in the context of Head and Neck Cancers
|
|
|
|
In: à paraître ; INTERSPEECH 2021 ; https://hal-univ-tlse3.archives-ouvertes.fr/hal-03269227 ; INTERSPEECH 2021, ISCA : International Speech and Communication Association, Aug 2021, Brno, Czech Republic ; https://www.interspeech2021.org (2021)
|
|
Abstract:
International audience ; The temporal dimension of speech acoustics is rarely taken into account in automatic models for Speech Intelligibility evaluation, although the rhythmic recurrence of phonemes, syllables and prosodic groups are allegedly good predictors of speech intelligibility. The present study aims at unravelling those automatic parameters that best account for the different levels of the speech signal's rhythmic structure, and to evaluate their correlation with a perceptual intelligibility measure. The parameters are extracted from the Fourier Transform of the amplitude modulation of the signal (Envelope Modulation Spectrum) [1, 2]. A Lasso linear model for feature selection is first implemented to select the most relevant parameters, and a SVR regression analysis is run to reveal the best parameters' combination. Our analyses of EMS, using data from the French corpora of cancer speech C2SI [3], show strong performances of the automatic prediction, with a correlation of 0.70 between our model and an intelligibility evaluation score by speech-pathologists. In particular, the highest correlation with speech intelligibility lies in the ratio between the energy in the low frequency band (0.5-4 Hz that represents slow rhythmic modulations indicative of prosodic groups) and in the higher one (4-10 Hz that represents fast rhythmic modulations like phonemes).
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing; Automatic Speech Processing; pathological speech; perceptual speech intelligibility; speech rhythm modeling
|
|
URL: https://hal-univ-tlse3.archives-ouvertes.fr/hal-03269227/file/Interspeech2021_1736_Paper.pdf https://hal-univ-tlse3.archives-ouvertes.fr/hal-03269227 https://hal-univ-tlse3.archives-ouvertes.fr/hal-03269227/document
|
|
BASE
|
|
Hide details
|
|
2 |
Construction of an automatic score for the evaluation of speech disorders among patients treated for a cancer of the oral cavity or the oropharynx: The Carcinologic Speech Severity Index
|
|
|
|
In: ISSN: 1043-3074 ; EISSN: 1097-0347 ; Head and Neck ; https://hal-univ-tlse3.archives-ouvertes.fr/hal-03413678 ; Head and Neck, Wiley, In press, ⟨10.1002/hed.26903⟩ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
C2SI corpus: a database of speech disorder productions to assess intelligibility and quality of life in head and neck cancers
|
|
|
|
In: ISSN: 1574-020X ; EISSN: 1574-0218 ; Language Resources and Evaluation ; https://hal.archives-ouvertes.fr/hal-02921918 ; Language Resources and Evaluation, Springer Verlag, 2021, 55 (1), pp.173-190. ⟨10.1007/s10579-020-09496-3⟩ ; https://link.springer.com/article/10.1007/s10579-020-09496-3 (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Analyse des performances des algorithmes d'estimation de la fréquence fondamentale dans le cadre de la voix pathologique
|
|
|
|
In: Séminaire AFCP 2021 – Phonétique Clinique ; https://hal-univ-tlse3.archives-ouvertes.fr/hal-03269235 ; Séminaire AFCP 2021 – Phonétique Clinique, May 2021, Toulouse (virtuel), France ; http://www.afcp-parole.org/seminaire-afcp-phonetique-clinique-27-mai-2021/ (2021)
|
|
BASE
|
|
Show details
|
|
6 |
Intelligibilité de la parole et qualité de vie. Réflexions à partir des résultats de l'étude «carcinologic speech severity index»
|
|
|
|
In: Actes des 8e Journees de Phonetique Clinique ; 8e Journees de Phonetique Clinique (JPC 2019) ; https://hal.archives-ouvertes.fr/hal-02453124 ; 8e Journees de Phonetique Clinique (JPC 2019), May 2019, Mons, Belgique. pp.15-16 (2019)
|
|
BASE
|
|
Show details
|
|
7 |
Evaluation de la compréhensibilité et conservation des fonctions prosodiques en perception de la parole de patients post traitement de cancers de la cavité buccale et du pharynx
|
|
|
|
In: XXXIIe Journées d'Etudes sur la Parole ; https://hal.archives-ouvertes.fr/hal-01962272 ; XXXIIe Journées d'Etudes sur la Parole, Jun 2018, Aix-en-Provence, France. pp.196-204, ⟨10.21437/jep.2018-23⟩ (2018)
|
|
BASE
|
|
Show details
|
|
8 |
Carcinologic Speech Severity Index Project: A Database of Speech Disorder Productions to Assess Quality of Life Related to Speech After Cancer
|
|
|
|
In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation - LREC 2018 ; Eleventh International Conference on Language Resources and Evaluation Conference (LREC 2018) ; https://hal.archives-ouvertes.fr/hal-01770168 ; Eleventh International Conference on Language Resources and Evaluation Conference (LREC 2018), May 2018, Miyazaki, Japan. pp.L18-1673 ; http://www.lrec-conf.org/proceedings/lrec2018/pdf/506.pdf (2018)
|
|
BASE
|
|
Show details
|
|
9 |
Neuropsycholinguistic Perspectives on Language Cognition ; Neuropsycholinguistic Perspectives on Language Cognition: Essays in honour of Jean-Luc Nespoulous
|
|
|
|
In: https://hal-univ-tlse2.archives-ouvertes.fr/hal-02159847 ; Corine Astésano; Mélanie Jucla. Psychology Press, 2017, 9780815356974 (2017)
|
|
BASE
|
|
Show details
|
|
10 |
Influence of musical expertise on the perception of pitch duration and intensity variations in speech and harmonic sounds
|
|
|
|
In: Neuropsycholinguistic Perspectives on Language Cognition: Essays in honour of Jean-Luc Nespoulous ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02159899 ; Corine Astésano; Mélanie Jucla. Neuropsycholinguistic Perspectives on Language Cognition: Essays in honour of Jean-Luc Nespoulous, Psychology Press, pp.88-102, 2017, 9780815356974 (2017)
|
|
BASE
|
|
Show details
|
|
11 |
Conservation des fonctions prosodiques post traitement des cancers de la cavité buccale et du pharynx
|
|
|
|
In: Actes des 7èmes Journées de Phonétique Clinique ; 7èmes Journées de Phonétique Clinique ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02159940 ; 7èmes Journées de Phonétique Clinique, Jun 2017, Paris, France. pp.59-60 ; http://jpc7.ilpga.fr/JPC7-ebook.pdf (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Perception of the Downstepped Final Accent in French
|
|
|
|
In: Proceedings of Phonetics and Phonology in Europe (PaPE) 2017 ; Phonetics and Phonology in Europe (PaPE) 2017 ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02159988 ; Phonetics and Phonology in Europe (PaPE) 2017, Jun 2017, Köln, Germany. pp.102-103 ; http://pape2017.uni-koeln.de/ (2017)
|
|
BASE
|
|
Show details
|
|
13 |
Evaluating prosodic similarity as a means towards L2 teacher's prosodic control training
|
|
|
|
In: Proceedings of Speech Prosody 2016 ; Speech Prosody 2016 ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02158918 ; Speech Prosody 2016, May 2016, Boston, United States. pp.26-30 ; http://sites.bu.edu/speechprosody2016/ (2016)
|
|
BASE
|
|
Show details
|
|
14 |
Stress and prosodic constituency in French : Issues in phonology and speech processing ; Accentuation et niveaux de constituance en français : enjeux phonologiques et psycholinguistiques
|
|
|
|
In: ISSN: 0023-8368 ; EISSN: 1957-7982 ; Langue française ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02149290 ; Langue française, Armand Colin, 2016, La prosodie du français : accentuation et phrasé, pp.11-30 ; https://www.revues.armand-colin.com/lettres-langues/langue-francaise/langue-francaise-ndeg-191-32016 (2016)
|
|
BASE
|
|
Show details
|
|
15 |
EEG investigation of prosodic cues processing in French
|
|
|
|
In: 22nd AMLaP Conference ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02160012 ; 22nd AMLaP Conference, Sep 2016, Bilbao, Spain. Proceedings of the 22nd AMLaP Conference, pp.70 ; https://www.bcbl.eu/events/amlap2016 (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Investigating the phonological status of the Initial Accent in French: an Event-Related Potentials study
|
|
|
|
In: Speech Prosody 2016 ; https://hal.archives-ouvertes.fr/hal-01577527 ; Speech Prosody 2016, May 2016, Boston, United States. ⟨10.21437/SpeechProsody.2016-243⟩ (2016)
|
|
BASE
|
|
Show details
|
|
17 |
EEG entrainment to the prosodic structure in spoken language
|
|
|
|
In: 22nd AMLaP Conference ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02160074 ; 22nd AMLaP Conference, Sep 2016, Bilbao, Spain. Proceedings of the 22nd AMLaP Conference, pp.71 ; https://www.bcbl.eu/events/amlap2016 (2016)
|
|
BASE
|
|
Show details
|
|
18 |
Naïve listeners' perception of prominence and boundary in French spontaneous speech
|
|
|
|
In: Speech Prosody ; https://hal.archives-ouvertes.fr/hal-01462259 ; Speech Prosody, May 2016, Boston, United States (2016)
|
|
BASE
|
|
Show details
|
|
19 |
Similitudes entre langage et musique : Etudes perceptives et de neuroimagerie
|
|
|
|
In: Journée des Masters LEx 2016 ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02163943 ; Journée des Masters LEx 2016, Apr 2016, Aix-en-Provence, France (2016)
|
|
BASE
|
|
Show details
|
|
20 |
Realization of the French initial accent: Stability and individual differences
|
|
|
|
In: Proceedings of the 7th conference on Tone and Intonation in Europe (TIE) ; 7th conference on Tone and Intonation in Europe (TIE) ; https://hal-univ-tlse2.archives-ouvertes.fr/hal-02160095 ; 7th conference on Tone and Intonation in Europe (TIE), Sep 2016, Canterbury, United Kingdom. pp.1-3 ; https://blogs.kent.ac.uk/tie-conference/ (2016)
|
|
BASE
|
|
Show details
|
|
|
|