Automatic speech recognition: A primer for speech-language pathology researchers

Keshet, Joseph

doi:10.1080/17549507.2018.1510033

Cited by 20 publications

(17 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In terms of resonance and articulation, these changes are typically embodied in vowel formant frequencies and acoustically perceived speech sounds 4 . Such speech indexes, in turn, carry abundant information about disease status 5 . Ideally, speech data are capable of indicating thorough details about the lesions, including the location, size, and degree of invasion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data mining of an acoustic biomarker in tongue cancers and its clinical validation

et al. 2021

View full text Add to dashboard Cite

The promise of speech disorders as biomarkers in clinical examination has been identified in a broad spectrum of neurodegenerative diseases. However, to the best of our knowledge, a validated acoustic marker with established discriminative and evaluative properties has not yet been developed for oral tongue cancers. Here we cross‐sectionally collected a screening dataset that included acoustic parameters extracted from 3 sustained vowels /ɑ/, /i/, /u/ and binary perceptual outcomes from 12 consonant‐vowel syllables. We used a support vector machine with linear kernel function within this dataset to identify the formant centralization ratio (FCR) as a dominant predictor of different perceptual outcomes across gender and syllable. The Acoustic analysis, Perceptual evaluation and Quality of Life assessment (APeQoL) was used to validate the FCR in 33 patients with primary resectable oral tongue cancers. Measurements were taken before (pre‐op) and four to six weeks after (post‐op) surgery. The speech handicap index (SHI), a speech‐specific questionnaire, was also administrated at these time points. Pre‐op correlation analysis within the APeQoL revealed overall consistency and a strong correlation between FCR and SHI scores. FCRs also increased significantly with increasing T classification pre‐operatively, especially for women. Longitudinally, the main effects of T classification, the extent of resection, and their interaction effects with time (pre‐op vs. post‐op) on FCRs were all significant. For pre‐operative FCR, after merging the two datasets, a cut‐off value of 0.970 produced an AUC of 0.861 (95% confidence interval: 0.785–0.938) for T3‐4 patients. In sum, this study determined that FCR is an acoustic marker with the potential to detect disease and related speech function in oral tongue cancers. These are preliminary findings that need to be replicated in longitudinal studies and/or larger cohorts.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Therefore, selecting proper acoustic features is of utmost importance. Abundant features of different physiological or psychological interpretations can be extracted based on acoustic, spectral, and cepstral measures from the speech signal 5 . Acoustic features typically include fundamental frequency (F0) and formant frequencies.…”

Section: Introductionmentioning

confidence: 99%

Data mining of an acoustic biomarker in tongue cancers and its clinical validation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Nowadays, it is indispensable not only for private use but also for various professions [ 3 ]. In several medical specialties, ASR has been tested and implemented in speech-language pathology research, diagnostics and therapeutics such as in speech apraxia [ 4 , 5 ]. Among medical professionals, ASR is commonly used to convert speech into text for data entries and has already been sufficiently tested in a mobile environment.…”

Section: Introductionmentioning

confidence: 99%

Automatic speech recognition in the operating room – An essential contemporary tool or a redundant gadget? A survey evaluation among physicians in form of a qualitative study

Schulte

Suarez-Ibarrola

Wegen

et al. 2020

Annals of Medicine and Surgery

View full text Add to dashboard Cite

Introduction For decades, automatic speech recognition (ASR) has been the subject of research and its range of applications broadened. Presently, ASR among physicians is mainly used to convert speech into text but not to implement instructions in the operating room (OR). This study aimed to evaluate physicians of different surgical professions on their personal experience and posture towards ASR. Methods A 16-item survey was distributed electronically to hospitals and outpatient clinics in southern Germany addressing physicians on the potential applications of ASR in the OR. Results The survey was responded by 185 of 2693 physicians (response rate: 6.9%) with a mean age of 41.8 ± 9.8 years. ASR is desirable in the OR regardless of the field of speciality (93.7%). While only 2.7% have used ASR, 87.9% evaluate its future potential as high. 91.0% of those working in a university hospital would consider testing ASR, while 67.5% of those in non-university hospitals and practices (p = 0.001). 90.1% of responders of strictly surgical specialities see potential in ASR while 73.7% in non-surgical specialities evaluate its future potential as high (p = 0.01). 58.3% of those over the age of 60 consider the use of ASR without a headset to be imaginable, while 96.3% among those under the age of 60. There were no statistically significant differences regarding sex and professional position. Conclusion Foreseeably, ASR is anticipated to be integrated into ORs and valued at a high market potential. Our study provides information about physicians’ individual preferences from various surgical disciplines regarding ASR.

show abstract

“…Developing dysarthric automatic speech recognition (ASR) is considered to be a challenging task due to the intra-and interspeaker variability in dysarthric speech and the difficulty of obtaining suitable data, that is, matched and in sufficient quantity [3,4]. Researchers have been working on developing and improving dysarthric ASR systems and employing different techniques to overcome the challenges such as using adaptation techniques and speaker dependent models [5,6,7,3]. None of those studies have focused on recognising any of the non-verbal, precisely paralinguistic, information such as the emotional state of the speaker.…”

Section: Introductionmentioning

confidence: 99%

Recognising Emotions in Dysarthric Speech Using Typical Speech Data

Alhinti¹,

Cunningham²,

Christensen³

2020

Interspeech 2020

View full text Add to dashboard Cite

show abstract

Automatic speech recognition: A primer for speech-language pathology researchers

Cited by 20 publications

References 55 publications

Data mining of an acoustic biomarker in tongue cancers and its clinical validation

Data mining of an acoustic biomarker in tongue cancers and its clinical validation

Automatic speech recognition in the operating room – An essential contemporary tool or a redundant gadget? A survey evaluation among physicians in form of a qualitative study

Recognising Emotions in Dysarthric Speech Using Typical Speech Data

Contact Info

Product

Resources

About