Matti D Groll1, Jennifer M Vojtech2, Surbhi Hablani3, Daryush D Mehta4, Daniel P Buckley5, J Pieter Noordzij6, Cara E Stepp7. 1. Department of Biomedical Engineering, Boston University, Boston, 02215, Massachusetts; Department of Speech, Language and Hearing Sciences, Boston University, Boston, 02215, Massachusetts. Electronic address: mgroll@bu.edu. 2. Department of Biomedical Engineering, Boston University, Boston, 02215, Massachusetts; Department of Speech, Language and Hearing Sciences, Boston University, Boston, 02215, Massachusetts. 3. Department of Speech, Language and Hearing Sciences, Boston University, Boston, 02215, Massachusetts. 4. Center for Laryngeal Surgery and Voice Rehabilitation and MGH Institute of Health Professions, Massachusetts General Hospital, Boston, 02114, Massachusetts; Department of Surgery, Harvard Medical School, Boston, 02144, Massachusetts; Program in Rehabilitation Sciences, MGH Institute of Health Professions, Boston, 02129, Massachusetts; Speech and Hearing Bioscience and Technology Program, Division of Medical Sciences, Harvard Medical School, Boston, 02144, Massachusetts. 5. Department of Speech, Language and Hearing Sciences, Boston University, Boston, 02215, Massachusetts; Department of Otolaryngology - Head and Neck Surgery, Boston University School of Medicine, Boston, 02118, Massachusetts. 6. Department of Otolaryngology - Head and Neck Surgery, Boston University School of Medicine, Boston, 02118, Massachusetts. 7. Department of Biomedical Engineering, Boston University, Boston, 02215, Massachusetts; Department of Speech, Language and Hearing Sciences, Boston University, Boston, 02215, Massachusetts; Department of Otolaryngology - Head and Neck Surgery, Boston University School of Medicine, Boston, 02118, Massachusetts.
Abstract
OBJECTIVE: Relative fundamental frequency (RFF) has been suggested as a potential acoustic measure of vocal effort. However, current clinical standards for RFF measures require time-consuming manual markings. Previous semi-automated algorithms have been developed to calculate RFF from microphone signals. The current study aimed to develop fully automated algorithms to calculate RFF from neck-surface accelerometer signals for ecological momentary assessment and ambulatory monitoring of voice. METHODS: Training a set of 2646 /vowel-fricative-vowel/ utterances from 317 unique speakers, with and without voice disorders, was used to develop automated algorithms to calculate RFF values from neck-surface accelerometer signals. The algorithms first rejected utterances with poor vowel-to-noise ratios, then identified fricative locations, then used signal features to determine voicing boundary cycles, and finally calculated corresponding RFF values. These automated RFF values were compared to the clinical gold-standard of manual RFF calculated from simultaneously collected microphone signals in a novel test set of 639 utterances from 77 unique speakers. RESULTS: Automated accelerometer-based RFF values resulted in an average mean bias error (MBE) across all cycles of 0.027 ST, with an MBE of 0.152 ST and -0.252 ST in the offset and onset cycles closest to the fricative, respectively. CONCLUSION: All MBE values were smaller than the expected changes in RFF values following successful voice therapy, suggesting that the current algorithms could be used for ecological momentary assessment and ambulatory monitoring via neck-surface accelerometer signals.
OBJECTIVE: Relative fundamental frequency (RFF) has been suggested as a potential acoustic measure of vocal effort. However, current clinical standards for RFF measures require time-consuming manual markings. Previous semi-automated algorithms have been developed to calculate RFF from microphone signals. The current study aimed to develop fully automated algorithms to calculate RFF from neck-surface accelerometer signals for ecological momentary assessment and ambulatory monitoring of voice. METHODS: Training a set of 2646 /vowel-fricative-vowel/ utterances from 317 unique speakers, with and without voice disorders, was used to develop automated algorithms to calculate RFF values from neck-surface accelerometer signals. The algorithms first rejected utterances with poor vowel-to-noise ratios, then identified fricative locations, then used signal features to determine voicing boundary cycles, and finally calculated corresponding RFF values. These automated RFF values were compared to the clinical gold-standard of manual RFF calculated from simultaneously collected microphone signals in a novel test set of 639 utterances from 77 unique speakers. RESULTS: Automated accelerometer-based RFF values resulted in an average mean bias error (MBE) across all cycles of 0.027 ST, with an MBE of 0.152 ST and -0.252 ST in the offset and onset cycles closest to the fricative, respectively. CONCLUSION: All MBE values were smaller than the expected changes in RFF values following successful voice therapy, suggesting that the current algorithms could be used for ecological momentary assessment and ambulatory monitoring via neck-surface accelerometer signals.
Authors: Harold A Cheyne; Helen M Hanson; Ronald P Genereux; Kenneth N Stevens; Robert E Hillman Journal: J Speech Lang Hear Res Date: 2003-12 Impact factor: 2.297
Authors: Matías Zañartu; Julio C Ho; Steve S Kraman; Hans Pasterkamp; Jessica E Huber; George R Wodicka Journal: IEEE Trans Biomed Eng Date: 2008-10-31 Impact factor: 4.538
Authors: Gail B Kempster; Bruce R Gerratt; Katherine Verdolini Abbott; Julie Barkmeier-Kraemer; Robert E Hillman Journal: Am J Speech Lang Pathol Date: 2008-10-16 Impact factor: 2.408
Authors: Victoria S McKenna; Elizabeth S Heller Murray; Yu-An S Lien; Cara E Stepp Journal: J Speech Lang Hear Res Date: 2016-12-01 Impact factor: 2.297
Authors: Daryush D Mehta; Jarrad H Van Stan; Matías Zañartu; Marzyeh Ghassemi; John V Guttag; Víctor M Espinoza; Juan P Cortés; Harold A Cheyne; Robert E Hillman Journal: Front Bioeng Biotechnol Date: 2015-10-16
Authors: Jennifer M Vojtech; Dante D Cilento; Austin T Luong; Jacob P Noordzij; Manuel Diaz-Cadiz; Matti D Groll; Daniel P Buckley; Victoria S McKenna; J Pieter Noordzij; Cara E Stepp Journal: Appl Sci (Basel) Date: 2021-04-23 Impact factor: 2.838