Depression Speaks: Automatic Discrimination between Depressed and Non-Depressed Speakers Based on Nonverbal Speech Features

Scibelli, Filomena; Roffo, Giorgio; Tayarani, Mohammad; Bartoli, Luca; Mattia, G. De; Esposito, Anna; Vinciarelli, Alessandro

doi:10.1109/icassp.2018.8461858

Cited by 15 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech technology offers promise because speaking is natural, can be used at a distance, requires no special training, and carries information about a speaker's state. A growing line of AI research has shown that depression can be detected from speech signals using natural language processing (NLP), acoustic models, and multimodal models [3], [4], [5], [6], [7], [8], [9], [10]. Common evaluations with shared data sets, features, and tools have recently led to progress, especially in modeling methods [11], [12], [13], [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Speech-Input Length for Speaker-Independent Depression Classification

Rutowski¹,

Harati²,

Lü³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Machine learning models for speech-based depression classification offer promise for health care applications. Despite growing work on depression classification, little is understood about how the length of speech-input impacts model performance. We analyze results for speakerindependent depression classification using a corpus of over 1400 hours of speech from a human-machine health screening application. We examine performance as a function of response input length for two NLP systems that differ in overall performance. Results for both systems show that performance depends on natural length, elapsed length, and ordering of the response within a session. Systems share a minimum length threshold, but differ in a response saturation threshold, with the latter higher for the better system. At saturation it is better to pose a new question to the speaker, than to continue the current response. These and additional reported results suggest how applications can be better designed to both elicit and process optimal input lengths for depression classification.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimizing Speech-Input Length for Speaker-Independent Depression Classification

Rutowski¹,

Harati²,

Lü³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…Research in the field of noise reduction is crucial if successful AI algorithms are to be developed. There are many research showing that processing voice signals can be helpful in extracting valuable information about people [642] , [643] , [644] . To the best of our knowledge, there is not much work performed on processing voice signals in identifying covid-19 patients.…”

Section: Conclusion Remarksmentioning

confidence: 99%

Applications of artificial intelligence in battling against covid-19: A literature review

2021

Chaos, Solitons & Fractals

161

View full text Add to dashboard Cite

show abstract

“…For example, in the medical field [69] observations are often difficult to collect (e.g., in the case of rare diseases), while the number of measurements performed on each sample can easily reach the order of thousands (e.g., set of DNA sequences). The small-sample, high-dimensional scenario holds in many other fields like business intelligence [70], geoscience [71] and the automatic analysis of behavioural cues and social signals [72], [73]).…”

Section: Challenge 1: Small-sample High-dimensionalmentioning

confidence: 99%

Infinite Feature Selection: A Graph-based Feature Filtering Approach

Roffo

Melzi

Castellani

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

124

View full text Add to dashboard Cite

We propose a filtering feature selection framework that considers a subset of features as a path in a graph, where a node is a feature and an edge indicates pairwise (customizable) relations among features, dealing with relevance and redundancy principles. By two different interpretations (exploiting properties of power series of matrices and relying on Markov chains fundamentals) we can evaluate the values of paths (i.e., feature subsets) of arbitrary lengths, eventually go to infinite, from which we dub our framework Infinite Feature Selection (Inf-FS). Going to infinite allows to constrain the computational complexity of the selection process, and to rank the features in an elegant way, that is, considering the value of any path (subset) containing a particular feature. We also propose a simple unsupervised strategy to cut the ranking, so providing the subset of features to keep. In the experiments, we analyze diverse setups with heterogeneous features, for a total of 11 benchmarks, comparing against 18 widely-know yet effective comparative approaches. The results show that Inf-FS behaves better in almost any situation, that is, when the number of features to keep are fixed a priori, or when the decision of the subset cardinality is part of the process.-Index Terms-Feature selection, filter methods, Markov chains.

show abstract

Depression Speaks: Automatic Discrimination between Depressed and Non-Depressed Speakers Based on Nonverbal Speech Features

Cited by 15 publications

References 14 publications

Optimizing Speech-Input Length for Speaker-Independent Depression Classification

Optimizing Speech-Input Length for Speaker-Independent Depression Classification

Applications of artificial intelligence in battling against covid-19: A literature review

Infinite Feature Selection: A Graph-based Feature Filtering Approach

Contact Info

Product

Resources

About