Search

Speech recordings are being more frequently used to detect and monitor disease, leading to privacy concerns. Beyond cryptography, protection of speech can be addressed by approaches, such as perturbation, disentanglement, and re-synthesis, that eliminate sensitive information of the speaker, leaving the information necessary for medical analysis purposes. In order for such privacy protective approaches to be developed, clear and systematic specifications of assumptions concerning medical settings and the needs of medical professionals are necessary. In this paper, we propose a Scenario of Use Scheme that incorporates an Attacker Model, which characterizes the adversary against whom the speaker's privacy must be defended, and a Protector Model, which specifies the defense. We discuss the connection of the scheme with previous work on speech privacy. Finally, we present a concrete example of a specified Scenario of Use and a set of experiments about protecting speaker data against gender inference attacks while maintaining utility for Parkinson's detection., Comment: Accepted and published at SPSC Symposium 2024 4th Symposium on Security and Privacy in Speech Communication. Interspeech 2024

Parkinson's disease (PD), the second most prevalent neurodegenerative disorder worldwide, frequently presents with early-stage speech impairments. Recent advancements in Artificial Intelligence (AI), particularly deep learning (DL), have significantly enhanced PD diagnosis through the analysis of speech data. Nevertheless, the progress of research is restricted by the limited availability of publicly accessible speech-based PD datasets, primarily due to privacy concerns. The goal of this systematic review is to explore the current landscape of speech-based DL approaches for PD classification, based on 33 scientific works published between January 2020 and March 2024. We discuss their available resources, capabilities, and potential limitations, and issues related to bias, explainability, and privacy. Furthermore, this review provides an overview of publicly accessible speech-based datasets and open-source material for PD. The DL approaches identified are categorized into end-to-end (E2E) learning, transfer learning (TL), and deep acoustic feature extraction (DAFE). Among E2E approaches, Convolutional Neural Networks (CNNs) are prevalent, though Transformers are increasingly popular. E2E approaches face challenges such as limited data and computational resources, especially with Transformers. TL addresses these issues by providing more robust PD diagnosis and better generalizability across languages. DAFE aims to improve the explainability and interpretability of results by examining the specific effects of deep features on both other DL approaches and more traditional machine learning (ML) methods. However, it often underperforms compared to E2E and TL approaches., Comment: van Gelderen, L., & Tejedor-Garc\'ia, C. (2024). Innovative Speech-Based Deep Learning Approaches for Parkinson's Disease Classification: A Systematic Review. Applied Sciences, 14(17). doi:10.3390/app14177873 This research was funded by the NWO research programme NGF AiNed Fellowship Grants under the project Responsible AI for Voice Diagnostics (RAIVD) - grant number NGF.1607.22.013

Automatic reading diagnosis systems can benefit both teachers for more efficient scoring of reading exercises and students for accessing reading exercises with feedback more easily. However, there are limited studies on Automatic Speech Recognition (ASR) for child speech in languages other than English, and limited research on ASR-based reading diagnosis systems. This study investigates how efficiently state-of-the-art (SOTA) pretrained ASR models recognize Dutch native children speech and manage to detect reading miscues. We found that Hubert Large finetuned on Dutch speech achieves SOTA phoneme-level child speech recognition (PER at 23.1\%), while Whisper (Faster Whisper Large-v2) achieves SOTA word-level performance (WER at 9.8\%). Our findings suggest that Wav2Vec2 Large and Whisper are the two best ASR models for reading miscue detection. Specifically, Wav2Vec2 Large shows the highest recall at 0.83, whereas Whisper exhibits the highest precision at 0.52 and an F1 score of 0.52., Comment: Proc. INTERSPEECH 2024, 1-5 September 2024. Kos Island, Greece

Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning. Voicebots, though, have largely been geared towards native adult speakers. We sought to assess the performance of two state-of-the-art ASR systems, Wav2Vec2.0 and Whisper AI, with a view to developing a voicebot that can support children acquiring a foreign language. We evaluated their performance on read and extemporaneous speech of native and non-native Dutch children. We also investigated the utility of using ASR technology to provide insight into the children's pronunciation and fluency. The results show that recent, pre-trained ASR transformer-based models achieve acceptable performance from which detailed feedback on phoneme pronunciation quality can be extracted, despite the challenging nature of child and non-native speech., Comment: Published on SLATE 2023, Esmad, Politecnico Do Porto, Portugal, 26-28 June, 2023, pp: 11:1-11:8

The interest in employing automatic speech recognition (ASR) in applications for reading practice has been growing in recent years. In a previous study, we presented an ASR-based Dutch reading tutor application that was developed to provide instantaneous feedback to first-graders learning to read. We saw that ASR has potential at this stage of the reading process, as the results suggested that pupils made progress in reading accuracy and fluency by using the software. In the current study, we used children's speech from an existing corpus (JASMIN) to develop two new ASR systems, and compared the results to those of the previous study. We analyze correct/incorrect classification of the ASR systems using human transcripts at word level, by means of evaluation measures such as Cohen's Kappa, Matthews Correlation Coefficient (MCC), precision, recall and F-measures. We observe improvements for the newly developed ASR systems regarding the agreement with human-based judgment and correct rejection (CR). The accuracy of the ASR systems varies for different reading tasks and word types. Our results suggest that, in the current configuration, it is difficult to classify isolated words. We discuss these results, possible ways to improve our systems and avenues for future research., Comment: Published (double-blind peer-reviewed) on SPECOM 2021

Automatic assessment of reading fluency using automatic speech recognition (ASR) holds great potential for early detection of reading difficulties and subsequent timely intervention. Precise assessment tools are required, especially for languages other than English. In this study, we evaluate six state-of-the-art ASR-based systems for automatically assessing Dutch oral reading accuracy using Kaldi and Whisper. Results show our most successful system reached substantial agreement with human evaluations (MCC = .63). The same system reached the highest correlation between forced decoding confidence scores and word correctness (r = .45). This system's language model (LM) consisted of manual orthographic transcriptions and reading prompts of the test data, which shows that including reading errors in the LM improves assessment performance. We discuss the implications for developing automatic assessment systems and identify possible avenues of future research.

Alzheimer's Disease (AD) is the world's leading neurodegenerative disease, which often results in communication difficulties. Analysing speech can serve as a diagnostic tool for identifying the condition. The recent ADReSS challenge provided a dataset for AD classification and highlighted the utility of manual transcriptions. In this study, we used the new state-of-the-art Automatic Speech Recognition (ASR) model Whisper to obtain the transcriptions, which also include automatic punctuation. The classification models achieved test accuracy scores of 0.854 and 0.833 combining the pretrained FastText word embeddings and recurrent neural networks on manual and ASR transcripts respectively. Additionally, we explored the influence of including pause information and punctuation in the transcriptions. We found that punctuation only yielded minor improvements in some cases, whereas pause encoding aided AD classification for both manual and ASR transcriptions across all approaches investigated.

In this paper we present SurvLIMEpy, an open-source Python package that implements the SurvLIME algorithm. This method allows to compute local feature importance for machine learning algorithms designed for modelling Survival Analysis data. Our implementation takes advantage of the parallelisation paradigm as all computations are performed in a matrix-wise fashion which speeds up execution time. Additionally, SurvLIMEpy assists the user with visualization tools to better understand the result of the algorithm. The package supports a wide variety of survival models, from the Cox Proportional Hazards Model to deep learning models such as DeepHit or DeepSurv. Two types of experiments are presented in this paper. First, by means of simulated data, we study the ability of the algorithm to capture the importance of the features. Second, we use three open source survival datasets together with a set of survival algorithms in order to demonstrate how SurvLIMEpy behaves when applied to different models.

JAX and PyTorch are two popular Python autodifferentiation frameworks. JAX is based around pure functions and functional programming. PyTorch has popularised the use of an object-oriented (OO) class-based syntax for defining parameterised functions, such as neural networks. That this seems like a fundamental difference means current libraries for building parameterised functions in JAX have either rejected the OO approach entirely (Stax) or have introduced OO-to-functional transformations, multiple new abstractions, and been limited in the extent to which they integrate with JAX (Flax, Haiku, Objax). Either way this OO/functional difference has been a source of tension. Here, we introduce `Equinox', a small neural network library showing how a PyTorch-like class-based approach may be admitted without sacrificing JAX-like functional programming. We provide two main ideas. One: parameterised functions are themselves represented as `PyTrees', which means that the parameterisation of a function is transparent to the JAX framework. Two: we filter a PyTree to isolate just those components that should be treated when transforming (`jit', `grad' or `vmap'-ing) a higher-order function of a parameterised function -- such as a loss function applied to a model. Overall Equinox resolves the above tension without introducing any new programmatic abstractions: only PyTrees and transformations, just as with regular JAX. Equinox is available at \url{https://github.com/patrick-kidger/equinox}., Comment: Accepted at the Differentiable Programming workshop at NeurIPS 2021

We present a set of algorithms implementing multidimensional scaling (MDS) for large data sets. MDS is a family of dimensionality reduction techniques using a $n \times n$ distance matrix as input, where $n$ is the number of individuals, and producing a low dimensional configuration: a $n\times r$ matrix with $r<

Could we use Computer Vision in the Internet of Things for using pictures as sensors? This is the principal hypothesis that we want to resolve. Currently, in order to create safety areas, cities, or homes, people use IP cameras. Nevertheless, this system needs people who watch the camera images, watch the recording after something occurred, or watch when the camera notifies them of any movement. These are the disadvantages. Furthermore, there are many Smart Cities and Smart Homes around the world. This is why we thought of using the idea of the Internet of Things to add a way of automating the use of IP cameras. In our case, we propose the analysis of pictures through Computer Vision to detect people in the analysed pictures. With this analysis, we are able to obtain if these pictures contain people and handle the pictures as if they were sensors with two possible states. Notwithstanding, Computer Vision is a very complicated field. This is why we needed a second hypothesis: Could we work with Computer Vision in the Internet of Things with a good accuracy to automate or semi-automate this kind of events? The demonstration of these hypotheses required a testing over our Computer Vision module to check the possibilities that we have to use this module in a possible real environment with a good accuracy. Our proposal, as a possible solution, is the analysis of entire sequence instead of isolated pictures for using pictures as sensors in the Internet of Things.

The Internet of Things is arriving to our homes or cities through fields already known like Smart Homes, Smart Cities, or Smart Towns. The monitoring of environmental conditions of cities can help to adapt the indoor locations of the cities in order to be more comfortable for people who stay there. A way to improve the indoor conditions is an efficient temperature control, however, it depends on many factors like the different combinations of outdoor temperature and humidity. Therefore, adjusting the indoor temperature is not setting a value according to other value. There are many more factors to take into consideration, hence the traditional logic based in binary states cannot be used. Many problems cannot be solved with a set of binary solutions and we need a new way of development. Fuzzy logic is able to interpret many states, more than two states, giving to computers the capacity to react in a similar way to people. In this paper we will propose a new approach to control the temperature using the Internet of Things together its platforms and fuzzy logic regarding not only the indoor temperature but also the outdoor temperature and humidity in order to save energy and to set a more comfortable environment for their users. Finally, we will conclude that the fuzzy approach allows us to achieve an energy saving around 40% and thus, save money.