Dementia affects the patient’s memory and leads to language impairment. Research has demonstrated that speech and language deterioration is often a clear indication of dementia and plays a crucial role in the recognition process. Even though earlier studies have used speech features to recognize subjects suffering from dementia, they are often used along with other linguistic features obtained from transcriptions. This study explores significant standalone speech features to recognize dementia. The primary contribution of this work is to identify a compact set of speech features that aid in the dementia recognition process. The secondary contribution is to leverage machine learning (ML) and deep learning (DL) models for the recognition task. Speech samples from the Pitt corpus in Dementia Bank are utilized for the present study. The critical speech feature set of prosodic, voice quality and cepstral features has been proposed for the task. The experimental results demonstrate the superiority of machine learning (87.6 percent) over deep learning (85 percent) models for recognizing Dementia using the compact speech feature combination, along with lower time and memory consumption. The results obtained using the proposed approach are promising compared with the existing works on dementia recognition using speech.
Abstract. This paper deals with convolution based image fusion using filter masks and reviews the performance of each with respect to qualitative and quantitative strategies. Fusion is performed using discrete wavelet transformation at two levels. The low and high frequency coefficients obtained are subjected to separate fusion rules. The low frequency approximation coefficients are selected based on a pixel selection rule while high frequency details are selected by convolution using averaging, gaussian, unsharp, prewitt and sobel filter masks of varying sizes. The performance evaluation in each case is conducted using objective strategies like RMSE and PSNR and results are graphically interpreted. Thus a comprehensive analysis is conducted to ensure the best fit mask for medical diagnosis and treatment applications.
Expressive speech can be synthesized using acoustic feature modeling by mapping the spectral and fundamental frequency parameters between neutral speech and target emotions based on context. Speaker and text-independent emotion conversion are challenging modeling problems in this paradigm. In this paper, spectral mapping using an i-vector-based framework of fixed dimensions is proposed for the speaker-independent emotion conversion, considering the entire problem in the utterance domain, rather than the existing approaches using frame-level processing. The high dimensionality of i-vectors and reduced utterances for i-vector training necessitate the use of Probabilistic Linear Discriminant Analysis (PLDA) to derive the emotion dependent latent vector. The i-vector setup does not require parallel data or alignment procedures at any stage of training. F 0 training is conducted on a multilayer feed-forward neural network using limited aligned seed parallel data. The framework is tested on three different languages (datasets) viz. German (EmoDB), Telugu (IITKGP), and English (SAVEE). The proposed approach delivered superior performance compared to the baseline under both clean and noisy data conditions considered for analysis. Under clean data conditions, the proposed model was found to perform better than the baseline with a Mel Cepstral Distortion as low as 3.8 (fear), an F 0-RMSE of 26.31 (happiness), and a Perceptual Evaluation of Speech Quality (PESQ) of 3.64 (anger) across datasets. Subjective testing provided a maximum CMOS of 4.10 (anger), 4.44 (fear), and 3.43 (happiness). INDEX TERMS CV-GMM, speech emotion, feed-forward ANN, i-vector, MFCC, PLDA. I. INTRODUCTION Emotions form a prominent para-linguistic element of human communication, consisting of speech, facial expressions, gestures, body language, etc. Among these, speech is the most readily accessible information source containing datapoints such as the message conveyed, speaker identity, gender, emotion, and speaker state of health. Emotions animate our speech and is essential for effective dialogue delivery in human-machine interaction and socio-cultural relationships. Furthermore, expressive speech synthesis finds applications The associate editor coordinating the review of this manuscript and approving it for publication was Kathiravan Srinivasan. in story-telling, speaking aids for the disabled [1]-[6], video games and speech-to-speech translators [7] to name a few. An expression synthesis system is normally added as a post-processing stage in text-to-speech synthesis (TTS) systems. There is often a need for a TTS synthesizer tested across multiple languages. This case is particularly relevant in multilingual countries such as India, where 22 official languages [8] exist along-with several other unofficial languages. Effective training of prosodic and spectral parameters from multiple languages is particularly useful in designing affective speech-to-speech translators in lowresource languages. Human-like dialogue delivery often encounters spontaneou...
We propose a hybrid network-based learning framework for speaker-adaptive vocal emotion conversion, tested on three different datasets (languages), namely, EmoDB (German), IITKGP (Telugu), and SAVEE (English). The optimized learning model introduced is unique because of its ability to synthesize emotional speech with an acceptable perceptive quality while preserving speaker characteristics. The multilingual model is extremely beneficial in scenarios wherein emotional training data from a specific target speaker are sparsely available. The proposed model uses speaker-normalized mel-generalized cepstral coefficients for spectral training with data adaptation using the seed data from the target speaker. The fundamental frequency (F0) is transformed using a wavelet synchrosqueezed transform prior to mapping to obtain a sharpened time-frequency representation. Moreover, a feedforward artificial neural network, together with particle swarm optimization, was used for F0 training. Additionally, static-intensity modification was also performed for each test utterance. Using the framework, we were able to capture the spectral and pitch contour variabilities of emotional expression better than with other state-of-the-art methods used in this study. Considering the overall performance scores across datasets, an average melcepstral distortion (MCD) of 4.98 and root mean square error (RMSE-F0) of 10.67 were obtained in objective evaluations, and an average comparative mean opinion score (CMOS) of 3.57 and speaker similarity score of 3.70 were obtained for the proposed framework. Particularly, the best MCD of 4.09 (EmoDB-happiness) and RMSE-F0 of 9.00 (EmoDB-anger) were obtained, along with the maximum CMOS of 3.7 and speaker similarity of 4.6, thereby highlighting the effectiveness of the hybrid network model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.