Heart rate is an important vital sign used in the diagnosis of many medical conditions. Conventionally, heart rate is measured using a medical device such as pulse oxymeter. Physiological parameters such as heart rate bear a correlation to speech characteristics of an individual. Hence, there is a possibility to measure heart rate from speech signals using machine learning and deep learning, which would also allow non-invasive, non contact based and remote monitoring of patients. However, to design such a scheme and verify its accuracy, it is necessary to collect speech recordings along with heart rates measured using a medical device, simultaneously during the recording. This article provides a dataset as well as the procedure used to create the dataset which could be used to facilitate research in developing techniques to estimate heart rate accurately by observing speech signal.
Nagoya Institute of Technology（名古屋工业大学）；Techno-Speech, Inc.（Techno-Speech公司）
This paper integrates a classic mel-cepstral synthesis filter into a modern neural speech synthesis system towards end-to-end controllable speech synthesis. Since the mel-cepstral synthesis filter is explicitly embedded in neural waveform models in the proposed system, both voice characteristics and the pitch of synthesized speech are highly controlled via a frequency warping parameter and fundamental frequency, respectively. We implement the mel-cepstral synthesis filter as a differentiable and GPU-friendly module to enable the acoustic and waveform models in the proposed system to be simulta…
University of Yamanashi（山梨大学）；Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences（医学、工学与农学综合研究生院）
In speech-related classification tasks, frequency-domain acoustic features such as logarithmic Mel-filter bank coefficients (FBANK) and cepstral-domain acoustic features such as Mel-frequency cepstral coefficients (MFCC) are often used. However, time-domain features perform more effectively in some sound classification tasks which contain non-vocal or weakly speech-related sounds. We previously proposed a feature called bit sequence representation (BSR), which is a time-domain binary acoustic feature based on the raw waveform. Compared with MFCC, BSR performed better in environmental sound det…
Enhanced Heart Sound Classification Using Mel Frequency Cepstral Coefficients and Comparative Analysis of Single vs. Ensemble Classifier Strategies
National Yunlin University of Science and Technology（云林科技大学）；Sejong University（世宗大学）；Islamic Azad University（伊斯兰阿扎德大学）；Prince Sattam bin Abdulaziz University（萨塔姆·本·阿卜杜勒-阿齐兹亲王大学）；Taif University（塔伊夫大学）；Lebanese French University（黎巴嫩法国大学）；UNSW Sydney（新南威尔士大学）；Duy Tan University（维新大学）
Comparative Analysis of Mel-Frequency Cepstral Coefficients and Wavelet Based Audio Signal Processing for Emotion Detection and Mental Health Assessment in Spoken Speech
Queen Mary University of London（伦敦玛丽女王大学）；The Alan Turing Institute（艾伦·图灵研究所）
Animal vocalisations contain important information about health, emotional state, and behaviour, thus can be potentially used for animal welfare monitoring. Motivated by the spectro-temporal patterns of chick calls in the time$-$frequency domain, in this paper we propose an automatic system for chick call recognition using the joint time$-$frequency scattering transform (JTFS). Taking full-length recordings as input, the system first extracts chick call candidates by an onset detector and silence removal. After computing their JTFS features, a support vector machine classifier groups each cand…
This study was carried out to enable individuals with limited mobility skills to play chess in real time and to play games with the individuals around them without being under any social distress or stress. Voice recordings were taken from 50 people (23 men and 27 women). While recording the sound, 29 words from each person were used which are determined as necessary for playing the game. Mel Frequency Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) qualification methods were used. In addition, k-NN, Naive Bayes and Neural Network classification methods were used for classificat…
Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with traditional speech LMs often depending on auxiliary text LMs for learning distributional aspects of the language. For the English language, these LMs treat words as atomic units, which presents inherent challenges to language modelling in the speech domain. In this paper, we propose a novel LSTM-based generative speech LM that is inspired by the CBOW model an…
Northwest University（西北大学）；University of Essex（埃塞克斯大学）
In this paper we present the Amharic Speech Emotion Dataset (ASED), which covers four dialects (Gojjam, Wollo, Shewa and Gonder) and five different emotions (neutral, fearful, happy, sad and angry). We believe it is the first Speech Emotion Recognition (SER) dataset for the Amharic language. 65 volunteer participants, all native speakers, recorded 2,474 sound samples, two to four seconds in length. Eight judges assigned emotions to the samples with high agreement level (Fleiss kappa = 0.8). The resulting dataset is freely available for download. Next, we developed a four-layer variant of the w…
One of the major parts of the voice recognition field is the choice of acoustic features which have to be robust against the variability of the speech signal, mismatched conditions, and noisy environments. Thus, different speech feature extraction techniques have been developed. In this paper, we investigate the robustness of several front-end techniques in Arabic speaker identification. We evaluate five different features in babble, factory and subway conditions at the various signal to noise ratios (SNR). The obtained results showed that two of the auditory feature i.e. gammatone frequency c…
LibriVAD: A Scalable Open Dataset with Deep Learning Benchmarks for Robust Voice Activity Detection
Department of Electronic Systems, Aalborg University, Denmark（电子系统系，奥胡斯大学，丹麦）；Pioneer Centre for AI, Denmark（人工智能先锋中心，丹麦）；Zoom Communications Inc., USA（Zoom通讯公司，美国）；Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge MA, USA（人工智能实验室，麻省理工学院，马萨诸塞州剑桥市，美国）
Sharif University of Technology（谢里夫理工大学）；University of Tehran（德黑兰大学）；University of Western Australia（西澳大学）
Cardiovascular Disease (CVD) is considered as one of the principal causes of death in the world. Over recent years, this field of study has attracted researchers' attention to investigate heart sounds' patterns for disease diagnostics. In this study, an approach is proposed for normal/abnormal heart sound classification on the Physionet challenge 2016 dataset. For the first time, a fixed-length feature vector; called i-vector; is extracted from each heart sound using Mel Frequency Cepstral Coefficient (MFCC) features. Afterwards, Principal Component Analysis (PCA) transform and Variational Aut…
Mehran University of Engineering and Technology（梅赫拉工程技术大学）；ADAPT – Science Foundation Ireland Research Centre（ADAPT——爱尔兰科学基金会研究中心）；Dublin City University（都柏林城市大学）；Lero – the Irish Software Research Centre（Lero——爱尔兰软件研究中心）；National University of Ireland, Galway（爱尔兰国立高威大学）
Deep Learning (DL) algorithms have shown impressive performance in diverse domains. Among them, audio has attracted many researchers over the last couple of decades due to some interesting patterns--particularly in classification of audio data. For better performance of audio classification, feature selection and combination play a key role as they have the potential to make or break the performance of any DL model. To investigate this role, we conduct an extensive evaluation of the performance of several cutting-edge DL models (i.e., Convolutional Neural Network, EfficientNet, MobileNet, Supp…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学与应用研究实验室）
Most of the speech processing applications use triangular filters spaced in mel-scale for feature extraction. In this paper, we propose a new data-driven filter design method which optimizes filter parameters from a given speech data. First, we introduce a frame-selection based approach for developing speech-signal-based frequency warping scale. Then, we propose a new method for computing the filter frequency responses by using principal component analysis (PCA). The main advantage of the proposed method over the recently introduced deep learning based methods is that it requires very limited …
Dhirubhai Ambani Institute of Information and Communication Technology（迪鲁巴伊·安巴尼信息与通信技术学院）；Indian Institute of Technology Jammu（印度理工学院查谟分校）
The recent advancements in generative artificial speech models have made possible the generation of highly realistic speech signals. At first, it seems exciting to obtain these artificially synthesized signals such as speech clones or deep fakes but if left unchecked, it may lead us to digital dystopia. One of the primary focus in audio forensics is validating the authenticity of a speech. Though some solutions are proposed for English speeches but the detection of synthetic Hindi speeches have not gained much attention. Here, we propose an approach for discrimination of AI synthesized Hindi s…
CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛里亚实验室）；Université de Lorraine（洛林大学）；School of Computing（计算机学院）；University of Eastern Finland（东芬兰大学）
We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification. Our architecture retains the simplicity and interpretability of MFCC-based features while allowing the model to be adapted to data flexibly. In practice, we formulate data-driven versions of the four linear transforms of a standard MFCC extractor -- windowing, discrete Fourier transform (DFT), mel filterbank and discrete cosine transform (DCT). Results reported reach up to 6.7\% (VoxCeleb1) and 9.7\% (SITW) relative improvement in term of eq…
University College Dublin（都柏林大学学院）；ADAPT SFI Research Centre（ADAPT SFI研究中心）
The objective of this work is to investigate complementary features which can aid the quintessential Mel frequency cepstral coefficients (MFCCs) in the task of closed, limited set word recognition for non-native English speakers of different mother-tongues. Unlike the MFCCs, which are derived from the spectral energy of the speech signal, the proposed frequency-centroids (FCs) encapsulate the spectral centres of the different bands of the speech spectrum, with the bands defined by the Mel filterbank. These features, in combination with the MFCCs, are observed to provide relative performance im…
The advent of learning-based methods in speech enhancement has revived the need for robust and reliable training features that can compactly represent speech signals while preserving their vital information. Time-frequency domain features, such as the Short-Term Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficients (MFCC), are preferred in many approaches. While the MFCC provide for a compact representation, they ignore the dynamics and distribution of energy in each mel-scale subband. In this work, a speech enhancement system based on Generative Adversarial Network (GAN) is impleme…
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread. The proposed model is composed of a carefully-tuned lightweight network designed by applying multiple network reduction and fidelity improvement techniques. In addition, we propose a novel group highway activation that can compromise between computational efficiency and the regularization effect of the gating mechanism. As well, we introduce a new metric called Elastic mel-cepstral distortion (EMCD) to measure the fidelity of the output mel-spectrogram. In experiments, we analy…
National University of Defense Technology（国防科技大学）；Army Engineering University of PLA（中国人民解放军陆军工程大学）
Traditional low bit-rate speech coding approach only handles narrowband speech at 8kHz, which limits further improvements in speech quality. Motivated by recent successful exploration of deep learning methods for image and speech compression, this paper presents a new approach through vector quantization (VQ) of mel-frequency cepstral coefficients (MFCCs) and using a deep generative model called WaveGlow to provide efficient and high-quality speech coding. The coding feature is sorely an 80-dimension MFCCs vector for 16kHz wideband speech, then speech coding at the bit-rate throughout 1000-200…
Speech Emotion Recognition Using MFCC Features and LSTM-Based Deep Learning Model
Department of Electrical Electronics and Telecommunications Engineering, Bells University of Technology（贝尔大学技术学院电子与电信工程系）；New Horizons Bells University of Technology（新希望贝尔大学技术学院）；Department of Computer Engineering, Bells University of Technology（贝尔大学技术学院计算机工程系）；Department of Computer and Information Sciences, Towson University（托逊大学计算机与信息科学系）
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）
This paper introduces scattering transform for speech emotion recognition (SER). Scattering transform generates feature representations which remain stable to deformations and shifting in time and frequency without much loss of information. In speech, the emotion cues are spread across time and localised in frequency. The time and frequency invariance characteristic of scattering coefficients provides a representation robust against emotion irrelevant variations e.g., different speakers, language, gender etc. while preserving the variations caused by emotion cues. Hence, such a representation …
Recently there has been a formidable work which has been put up from the people who are working in the frontlines such as hospitals, clinics, and labs alongside researchers and scientists who are also putting tremendous efforts in the fight against COVID-19 pandemic. Due to the preposterous spread of the virus, the integration of the artificial intelligence has taken a considerable part in the health sector, by implementing the fundamentals of Automatic Speech Recognition (ASR) and deep learning algorithms. In this paper, we illustrate the importance of speech signal processing in the extracti…
