Automated techniques to detect Alzheimer’s Dementia through the use of audio recordings of spontaneous speech are now available with varying degrees of reliability. Here, we present a systematic comparison across different modalities, granularities and machine learning models to guide in choosing the most effective tools. Specifically, we present a multi-modal approach (audio and text) for the automatic detection of Alzheimer’s Dementia from recordings of spontaneous speech. Sixteen features, including four feature extraction methods (Energy–Time plots, Keg of Text Analytics, Keg of Text Analytics-Extended and Speech to Silence ratio) not previously applied in this context were tested to determine their relative performance. These features encompass two modalities (audio vs. text) at two resolution scales (frame-level vs. file-level). We compared the accuracy resulting from these features and found that text-based classification outperformed audio-based classification with the best performance attaining 88.7%, surpassing other reports to-date relying on the same dataset. For text-based classification in particular, the best file-level feature performed 9.8% better than the frame-level feature. However, when comparing audio-based classification, the best frame-level feature performed 1.4% better than the best file-level feature. This multi-modal multi-model comparison at high- and low-resolution offers insights into which approach is most efficacious, depending on the sampling context. Such a comparison of the accuracy of Alzheimer’s Dementia classification using both frame-level and file-level granularities on audio and text modalities of different machine learning models on the same dataset has not been previously addressed. We also demonstrate that the subject’s speech captured in short time frames and their dynamics may contain enough inherent information to indicate the presence of dementia. Overall, such a systematic analysis facilitates the identification of Alzheimer’s Dementia quickly and non-invasively, potentially leading to more timely interventions and improved patient outcomes.

Purpose: The purpose of this research note is to provide a performance comparison of available algorithms for the automated evaluation of oral diadochokinesis using speech samples from patients with amyotrophic lateral sclerosis (ALS). Method: Four different algorithms based on a wide range of signal processing approaches were tested on a sequential motion rate /pa/-/ta/-/ka/ syllable repetition paradigm collected from 18 patients with ALS and 18 age- and gender-matched healthy controls (HCs). Results: The best temporal detection of syllable position for a 10-ms tolerance value was achieved for ALS patients using a traditional signal processing approach based on a combination of filtering in the spectrogram, Bayesian detection, and polynomial thresholding with an accuracy rate of 74.4%, and for HCs using a deep learning approach with an accuracy rate of 87.6%. Compared to HCs, a slow diadochokinetic rate ( p < .001) and diadochokinetic irregularity ( p < .01) were detected in ALS patients. Conclusions: The approaches using deep learning or multiple-step combinations of advanced signal processing methods provided a more robust solution to the estimation of oral DDK variables than did simpler approaches based on the rough segmentation of the signal envelope. The automated acoustic assessment of oral diadochokinesis shows excellent potential for monitoring bulbar disease progression in individuals with ALS.

Accent is a crucial aspect of speech that helps define one's identity. We note that the state-of-the-art Text-to-Speech (TTS) systems can achieve high-quality generated voice, but still lack in terms of versatility and customizability. Moreover, they generally do not take into account accent, which is an important feature of speaking style. In this work, we utilize the concept of Multi-level VAE (ML-VAE) to build a control mechanism that aims to disentangle accent from a reference accented speaker; and to synthesize voices in different accents such as English, American, Irish, and Scottish. The proposed framework can also achieve high-quality accented voice generation for multi-speaker setup, which we believe is remarkable. We investigate the performance through objective metrics and conduct listening experiments for a subjective performance assessment. We showed that the proposed method achieves good performance for naturalness, speaker similarity, and accent similarity.

Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority group listeners, and useful across various applications and context. Speech synthesis can further be made more flexible by allowing users to choose any combination of speaker identity and accent, resulting in a wide range of personalized speech outputs. Current models struggle to disentangle speaker and accent representation, making it difficult to accurately imitate different accents while maintaining the same speaker characteristics. We propose a novel approach to disentangle speaker and accent representations using multi-level variational autoencoders (ML-VAE) and vector quantization (VQ) to improve flexibility and enhance personalization in speech synthesis. Our proposed method addresses the challenge of effectively separating speaker and accent characteristics, enabling more fine-grained control over the synthesized speech. Code and speech samples are publicly available.

Binaural hearing is an important ability of humans. While utilizing a binaural hearing model with Artificial Neural Network it is possible to simulate localization of sound source position by humans. In this paper localization of drum kit sounds as well as localization prediction dependence on head related functions used to synthesize these drum kit sounds are concerned. Three separate tests were performed using two classification algorithms: for horizontal plane only, for both horizontal and vertical planes (Koshkina E., Bouse J., Proc. of Poster 2017). In the first test localization of auralized drum kit sounds through different HRTF sets at fixed positions was performed to observe elevation and azimuth prediction differences. In the other two tests localization at unfixed positions for drum kit sounds with and without room reflections was performed.