Automatic Evaluation of Speech Intelligibility Based on I-vectors in the Context of Head and Neck Cancers

Laaridh, Imed; Fredouille, Corinne; Ghio, Alain; Lalain, Muriel; Woisard, Virginie

doi:10.21437/interspeech.2018-1266

Cited by 17 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Figure 2 depicts the predicted intelligibility values compared to the professional perceptual assessment. The correlation values achieved are consistent with the ones found in previous studies such as [12], which achieved correlation values between 0.75 and 0.84. However it is important to state that the perceptual intelligibility measures, in our case, are far more subjective due to being rated by health professionals instead of naive listeners.…”

Section: Evaluation Scoressupporting

confidence: 91%

“…Concerning the results of the perceptual assessment, the intelligibility measures used suffered, in some cases, from very high variance within the same speaker, reaching standard deviations of up to 3 (on a 0-10 scale), pinpointing the large interclass variance present in this type of clinical assessments [4]. This aspect points out the subjectivity of the intelligibility scores used, when compared to the more objective ones found previously in the literature [12], which were rated by naive listeners instead of health professionals. When comparing the usage of i-vectors with the x-vector paradigm, we can conclude that the latter does not rely on larger amounts of data to output better results [13].…”

Section: Perspectivesmentioning

confidence: 98%

“…In [11], we can see approaches based on i-vectors that aim to predict dysarthric speech evaluation metrics like intelligibility, severity and articulation impairment. In [12], the speaker embedding paradigm was applied to the specific case of intelligibility in the same HNC corpus. The study used the recording of a vast list of pseudo-words and addressed intelligibility as the phonetic distance between the original and the perceived word.…”

Section: Introductionmentioning

confidence: 99%

“…Recent advances suggest that x-vectors have been successfully applied to paralinguistic tasks such as emotion recognition [16], and to the detection of diseases like Obstructive Sleep Apnea [17] and Alzheimer's [18]. Following the line of research present in [11] and [12], we investigate the reliability of using x-vector speaker embeddings as features for automatic intelligibility prediction in the context of HNC. We perform comparisons between the automatic predicted scores and the perceptual evaluation issued by the professional assessment of dysarthria and healthy speakers.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Prediction of Speech Intelligibility Based on X-Vectors in the Context of Head and Neck Cancer

Quintas¹,

Mauclair²,

Woisard³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

In the context of pathological speech, perceptual evaluation is still the most widely used method for intelligibility estimation. Despite being considered a staple in clinical settings, it has a well-known subjectivity associated with it, which results in greater variances and low reproducibility. On the other hand, due to the increasing computing power and latest research, automatic evaluation has become a growing alternative to perceptual assessments. In this paper we investigate an automatic prediction of speech intelligibility using the x-vector paradigm, in the context of head and neck cancer. Experimental evaluation of the proposed model suggests a high correlation rate when applied to our corpus of HNC patients (p = 0.85). Our approach also displayed the possibility of achieving very high correlation values (p = 0.95) when adapting the evaluation to each individual speaker, displaying a significantly more accurate prediction whilst using smaller amounts of data. These results can also provide valuable insight to the redevelopment of test protocols, which typically tend to be substantial and effort-intensive for patients.

show abstract

Section: Evaluation Scoressupporting

confidence: 91%

Section: Perspectivesmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Prediction of Speech Intelligibility Based on X-Vectors in the Context of Head and Neck Cancer

Quintas¹,

Mauclair²,

Woisard³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Perceptual evaluations are in progress in order to complete the usable metadata, and to obtain reliable intelligibility/comprehensibility scores, which will be compared to self-assessed quality of life scores. We are also working now on extracting information from the different recordings in order to analyze them and to produce automatic indexes [28,16,15,11]. This is our main goal to get objective judgments, which can help speech therapists and physicians in clinical practice.…”

Section: Discussionmentioning

confidence: 99%

C2SI corpus: a database of speech disorder productions to assess intelligibility and quality of life in head and neck cancers

Woisard¹,

Astésano

Balaguer³

et al. 2020

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

Within the framework of the Carcinologic Speech Severity Index (C2SI) INCaProject, we collected a large database of French speech recordings aiming at validatingDisorder Severity Indexes. Such a database will be useful for measuring the impact of oraland pharyngeal cavity cancer on speech production. It will permit to assess patients Qualityof Life after treatment. The database is composed of audio recordings from 134 sessions andassociated metadata. Several intelligibility and comprehensibility levels of speech functionshave been evaluated. Acoustics and prosody have been assessed. Perceptual evaluation ratesfrom both naive and expert juries are being produced. Automatic analyzes are being carriedout. It is intended to provide speech therapists and physicians with objective tools, whichtake into account the intelligibility and comprehensibility of patients which received cancertreatment (surgery and/or radiotherapy and/or chemotherapy). The aim of this paper is tojustify the necessity of such a corpus and to present its data collection. This C2SI corpus willbe available to the scientific community through the Scientific Interest Group Parolotheque.

show abstract

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Speech disorders impact quality of life for patients treated with oral cavity and oropharynx cancers. However, there is a lack of uniform and applicable methods for measuring the impact on speech production after treatment in this tumor location. Objective The objective of this work is to (1) model an automatic severity index of speech applicable in clinical practice, that is equivalent or superior to a severity score obtained by human listeners, via several acoustics parameters extracted (a) directly from speech signal and (b) resulting from speech processing and (2) derive an automatic speech intelligibility classification (i.e., mild, moderate, severe) to predict speech disability and handicap by combining the listener comprehension score with self‐reported quality of life related to speech. Methods Eighty‐seven patients treated for cancer of the oral cavity or the oropharynx and 35 controls performed different tasks of speech production and completed questionnaires on speech‐related quality of life. The audio recordings were then evaluated by human perception and automatic speech processing. Then, a score was developed through a classic logistic regression model allowing description of the severity of patients' speech disorders. Results Among the group of parameters subject to extraction from automatic processing of the speech signal, six were retained, producing a correlation at 0.87 with the perceptual reference score, 0.77 with the comprehension score, and 0.5 with speech‐related quality of life. The parameters that contributed the most are based on automatic speech recognition systems. These are mainly the automatic average normalized likelihood score on a text reading task and the score of cumulative rankings on pseudowords. The reduced automatic YC2SI is modeled in this way: YC2SIp = 11.48726 + (1.52926 × Xaveraged normalized likelihood reading) + (−1.94e‐06 × Xscore of cumulative ranks pseudowords). Conclusion Automatic processing of speech makes it possible to arrive at valid, reliable, and reproducible parameters able to serve as references in the framework of follow‐up of patients treated for cancer of the oral cavity or the oropharynx.

show abstract

Automatic Evaluation of Speech Intelligibility Based on I-vectors in the Context of Head and Neck Cancers

Cited by 17 publications

References 23 publications

Automatic Prediction of Speech Intelligibility Based on X-Vectors in the Context of Head and Neck Cancer

Automatic Prediction of Speech Intelligibility Based on X-Vectors in the Context of Head and Neck Cancer

C2SI corpus: a database of speech disorder productions to assess intelligibility and quality of life in head and neck cancers

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

Contact Info

Product

Resources

About