Comparing Acoustic-based Approaches for Alzheimer's Disease Detection

Balagopalan, Aparna; Novikova, Jekaterina

doi:10.48550/arxiv.2106.01555

Cited by 5 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SSL models are specifically proposed for speech representations, such as TRILL [19], PACE+ [46], Mockingjay [39], Wav2Vec 2.0 [40], and HuBERT [41]. In particular, non-speech recognition application studies such as [7] use Wav2Vec 2.0 as a feature extractor.…”

Section: B Audio Pre-training Methodsmentioning

confidence: 99%

“…Temporal pooling ablation results of (6) mean or (7) max pooling show that max pooling performs better than mean pooling on five tasks with a margin of 3.0 to 8.7%, indicating that max pooling can be more advantageous in general. While the (1) combination of both statistics slightly degrades performance on some tasks, it improves on average, showing that tasks benefit from the combination of these statistics.…”

Section: F Ablations Of Encoder Global Pooling Blocksmentioning

confidence: 99%

“…P RE-trained models play a vital role as feature extractors in various domains, e.g., BERT [1] in the natural language processing domain and ImageNet pre-trained models [2]- [4] in the image domain. In the audio domain, pre-trained models (e.g., VGGish [5]) have enabled recent advances in applications such as heart sound classification [6], Alzheimer's disease detection [7], conservation monitoring [8], audio captioning [9], audio retrieval [10], and so forth.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

BYOL for Audio: Exploring Pre-Trained General-Purpose Audio Representations

Niizumi

Takeuchi

Ohishi

et al. 2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Pre-trained models are essential as feature extractors in modern machine learning systems in various domains. In this study, we hypothesize that representations effective for general audio tasks should provide multiple aspects of robust features of the input sound. For recognizing sounds regardless of perturbations such as varying pitch or timbre, features should be robust to these perturbations. For serving the diverse needs of tasks such as recognition of emotions or music genres, representations should provide multiple aspects of information, such as local and global features. To implement our principle, we propose a self-supervised learning method: Bootstrap Your Own Latent (BYOL) for Audio (BYOL-A, pronounced "viola"). BYOL-A pretrains representations of the input sound invariant to audio data augmentations, which makes the learned representations robust to the perturbations of sounds. Whereas the BYOL-A encoder combines local and global features and calculates their statistics to make the representation provide multi-aspect information. As a result, the learned representations should provide robust and multi-aspect information to serve various needs of diverse tasks. We evaluated the general audio task performance of BYOL-A compared to previous state-of-the-art methods, and BYOL-A demonstrated generalizability with the best average result of 72.4% and the best VoxCeleb1 result of 57.6%. Extensive ablation experiments revealed that the BYOL-A encoder architecture contributes to most performance, and the final critical portion resorts to the BYOL framework and BYOL-A augmentations. Our code is available online for future studies.

show abstract

Section: B Audio Pre-training Methodsmentioning

confidence: 99%

Section: F Ablations Of Encoder Global Pooling Blocksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BYOL for Audio: Exploring Pre-Trained General-Purpose Audio Representations

Niizumi

Takeuchi

Ohishi

et al. 2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…SSL models are specifically proposed for speech representations, including Wav2Vec 2.0 [42], PACE+ [43], and TRILL [19]. In particular, Wav2Vec 2.0 was fine-tuned on the automatic speech recognition (ASR) task and provided state-of-the-art performance, and it has also been used in non-ASR application studies [7].…”

Section: B Audio Pre-training Methodsmentioning

confidence: 99%

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

Niizumi

Takeuchi

Ohishi

et al. 2021

2021 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Pre-trained models are essential as feature extractors in modern machine learning systems in various domains. In this study, we hypothesize that representations effective for general audio tasks should provide multiple aspects of robust features of the input sound. For recognizing sounds regardless of perturbations such as varying pitch or timbre, features should be robust to these perturbations. For serving the diverse needs of tasks such as recognition of emotions or music genres, representations should provide multiple aspects of these robust features, such as local and global features and their statistics. To implement our principle, we propose a self-supervised learning method: Bootstrap Your Own Latent (BYOL) for Audio (BYOL-A, pronounced "viola"). BYOL-A pre-trains representations of the input sound themselves invariant to audio data augmentations by minimizing the difference between a pair of augmented input variants, which makes the learned representations robust to the perturbations of sounds. In the BYOL-A encoder, the global pooling calculates representations to form multi-aspect information by combining statistics of frequency-and channelwise, local, and global features. As a result, the learned representations should provide multi-aspect robust features of the input and serve various needs of diverse tasks. We evaluated general audio task performance among previous state-of-the-art methods, and BYOL-A showed competitive results in all tasks with the best average result of 72.4 %. Besides, BYOL-A sets new records of 57.6 % on VoxCeleb1 and 63.8 % on CREMA-D. We also conducted extensive ablation experiments and validated the contributions of BYOL-A components. Our code is available online.

show abstract

“…Once sound is converted to textual information, signals that should have been present are missing as a result of dementia. There are models that use both speech signals and textual information to predict the risk of dementia (19).…”

Section: Early Models For Detection Of Dementia Using Deep Learningmentioning

confidence: 99%