Voice control is an important way of controlling mobile devices; however, using it remains a challenge for dysarthric patients. Currently, there are many approaches, such as automatic speech recognition (ASR) systems, being used to help dysarthric patients control mobile devices. However, the large computation power requirement for the ASR system increases implementation costs. To alleviate this problem, this study proposed a convolution neural network (CNN) with a phonetic posteriorgram (PPG) speech feature system to recognize speech commands, called CNN–PPG; meanwhile, the CNN model with Mel-frequency cepstral coefficient (CNN–MFCC model) and ASR-based systems were used for comparison. The experiment results show that the CNN–PPG system provided 93.49% accuracy, better than the CNN–MFCC (65.67%) and ASR-based systems (89.59%). Additionally, the CNN–PPG used a smaller model size comprising only 54% parameter numbers compared with the ASR-based system; hence, the proposed system could reduce implementation costs for users. These findings suggest that the CNN–PPG system could augment a communication device to help dysarthric patients control the mobile device via speech commands in the future.

This brief introduces an innovative recursive discrete cosine transform (DCT) algorithm characterized by its exceptional precision and minimal multiplication requirements. Through the strategic implementation of data reordering and “q” value adjustment schemes, the proposed algorithm entails only a single constant-multiplication operation featuring a fixed cosine coefficient within the iterative phase. By judiciously selecting an appropriate “q” value (q =41), it achieves outstanding results, reaching peak signal-to-noise ratios (PSNRs) of 94.9 and 100.9 dB under 18-bit and 20-bit word length (WL) conditions, respectively, in terms of decimal places. Notably, the proposed algorithm substantially diminishes the number of multiplications by 86.08%, offset by an increase of 2688 additions. The proposed design has a simpler structure and utilizes fewer hardware resources. In field programmable gate array (FPGA) implementation, the device is composed of 43 combinational adaptive look-up tables (ALUTs) specifically allocated for constant multiplication (CM). Overall, the proposed accelerator totally takes 158 combinational ALUTs, 65 registers, a 960-bit read-only memory (ROM), and a 1024-bit random access memory (RAM) in hardware realization and can be operated at a maximum frequency of 156.62 MHz. Therefore, it is particularly well-suited for VLSI implementation in a parallel calculation of Mel-scale frequency cepstral coefficients (MFCCs).

When a band is performing at a public occasion, certain sound effects are expected to be added to enliven the atmosphere. To achieve this effect, microphones and instruments are all connected to an audio mixer, then the expected audio output will be played through the speakers. However, sound engineers always spend plenty of time tuning the mixer until the satisfied results are obtained. This paper presents a smart digital mixer system that integrates touch control, speech control, and commonly used functions on an Android mobile platform to improve the mobility of audio mixer while tuning. The proposed system adopts a digital signal processor (DSP) as the core of the hardware architecture. The application provides a UI interface on an Android mobile phone in order to achieve the functions of speech recognition and touch control. The control commands will be transmitted to DSP via Bluetooth 5.0, self-defined Bluetooth packet format (SBPF), and data transfer controller (DTC). The main contribution of this work is to propose multiple functions of a mixer system with a convenient and interactive user interface. The experimental results show the average accuracy of all respondents reached 92.3%. Moreover, the proposed system has the advantage of having a low-cost hardware circuit design, and provides high flexibility of setting for the audio mixer system according to the user’s preference.

As voice cloning technology rapidly advances, the risk of personal voices being misused by malicious actors for fraud or other illegal activities has significantly increased, making the collection of speech data increasingly challenging. To address this issue, this study proposes a data augmentation method based on XText-to-Speech (XTTS) synthesis to tackle the challenges of small-sample, multi-class speech recognition, using profanity as a case study to achieve high-accuracy keyword recognition. Two models were therefore evaluated: a CNN model (Proposed-I) and a CNN-Transformer hybrid model (Proposed-II). Proposed-I leverages local feature extraction, improving accuracy on a real human speech (RHS) test set from 55.35% without augmentation to 80.36% with XTTS-enhanced data. Proposed-II integrates CNN’s local feature extraction with Transformer’s long-range dependency modeling, further boosting test set accuracy to 88.90% while reducing the parameter count by approximately 41%, significantly enhancing computational efficiency. Compared to a previously proposed incremental architecture, the Proposed-II model achieves an 8.49% higher accuracy while reducing parameters by about 98.81% and MACs by about 98.97%, demonstrating exceptional resource efficiency. By utilizing XTTS and public corpora to generate a novel keyword speech dataset, this study enhances sample diversity and reduces reliance on large-scale original speech data. Experimental analysis reveals that an optimal synthetic-to-real speech ratio of 1:5 significantly improves the overall system accuracy, effectively addressing data scarcity. Additionally, the Proposed-I and Proposed-II models achieve accuracies of 97.54% and 98.66%, respectively, in distinguishing real from synthetic speech, demonstrating their strong potential for speech security and anti-spoofing applications.

This study proposes a comprehensive and computationally efficient system for the recognition of heart valve diseases (HVDs) in phonocardiogram (PCG) signals, emphasizing an end-to-end workflow suitable for real-world deployment. The core of the system is a lightweight weighted convolutional neural network (WCNN) featuring a key weighting calculation (KWC) layer, which enhances noise robustness by adaptively weighting feature map channels based on global average pooling. The proposed system incorporates optimized feature extraction using Mel-frequency cepstral coefficients (MFCCs) guided by GradCAM, and a band energy ratio (BER) metric to assess signal quality, showing that lower BER values are associated with higher misclassification rates due to noise. Experimental results demonstrated classification accuracies of 99.6% and 90.74% on the GitHub PCG and PhysioNet/CinC Challenge 2016 databases, respectively, where the models were trained and tested independently. The proposed model achieved superior accuracy using significantly fewer parameters (312,357) and lower computational cost (4.5 M FLOPs) compared with previously published research. Compared with the model proposed by Karhade et al., the proposed model use 74.9% fewer parameters and 99.3% fewer FLOPs. Furthermore, the proposed model was implemented on a Raspberry Pi, achieving real-time HVDs detection with a detection time of only 1.87 ms for a 1.4 s signal.