Objective:To discuss the current clinical application and usefulness,shortcomings and future directions of traditional and artificial intelligence(AI)-driven acoustic assessment techniques to detect voice dysfunction....Objective:To discuss the current clinical application and usefulness,shortcomings and future directions of traditional and artificial intelligence(AI)-driven acoustic assessment techniques to detect voice dysfunction.Data Sources:Literature review.Conclusion:AI-based acoustic voice analysis techniques have huge potential to improve the early recognition,diagnosis,and tracking of treatment success in patients with voice disorders or diseases affecting voice function.Through smartphones,wearable devices,and server-based solutions,acoustic voice assessment techniques have become widely available and may be extended to workplace and private settings.However,the transformative potential is thwarted by several limitations including a lack of(a)consistent data collection and reporting standards,leading to heterogeneity of current databases and literature;(b)characterization what acoustic analysis techniques including AI can detect or track reliably,and whether the derived outcomes serve as a reliable marker of dysfunction,pathology,or an improvement thereof;(c)clinical validation studies in unselected patients;and(d)ethical and legal controversies.Thus,substantial effort to research,define and establish guidelines for the collection,storage,and processing of acoustic data and valid clinical applications is warranted to designsensible strategies for analysis and use.展开更多
Neurological voice disorders,such as Parkinson's disease,laryngeal dystonia,and stroke-induced dysarthria,significantly impact speech production and communication.Traditional diagnostic methods rely on subjective ...Neurological voice disorders,such as Parkinson's disease,laryngeal dystonia,and stroke-induced dysarthria,significantly impact speech production and communication.Traditional diagnostic methods rely on subjective assessment,whereas artificial intelligence(AI)offers objective,noninvasive,and scalable solutions for voice analysis.This review examines the applications,advancements,challenges,and future prospects of AI-driven methods in diagnosing,monitoring,and treating neurological voice disorders.We analyze recent advances in AI-based voice analysis,including machine learning,deep learning and signal processing techniques,and evaluate their effectiveness based on existing literature.AI models have demonstrated high accuracy in detecting subtle voice impairments,enabling early diagnosis of voice disorders,and predicting treatment response.Deep learning methods,particularly convolutional and transformer-based networks,have been effective in extracting meaningful biomarkers from acoustic or other modality data.Despite these promising advances,challenges remain,including limited high-quality data sets on some rare neurological voice disorders,ethical concerns regarding patient privacy,and the need for broad clinical validation.Further research should focus on developing standardized data sets,improving the ability of the AI model to learn representations,and enhancing its generalizability.With further development,AI-driven data analysis has the potential to transform the early detection and management of neurological voice disorders.展开更多
As the widespread employment of firewalls on the Internet, user datagram protocol（UDP） based voice over Internet protocol（Vo IP） system will be unable to transmit voice data. This paper proposed a novel method to ...As the widespread employment of firewalls on the Internet, user datagram protocol（UDP） based voice over Internet protocol（Vo IP） system will be unable to transmit voice data. This paper proposed a novel method to transmit voice data based on transmission control protocol（TCP）. The method adopts a disorder TCP transmission strategy, which allows discontinuous data packets in TCP queues read by application layer directly without waiting for the retransmission of lost data packets. A byte stream data boundary identification algorithm based on consistent overhead byte stuffing algorithm is designed to efficiently identify complete voice data packets from disordered TCP packets arrived so as to transmit the data to the audio processing module timely. Then, by implementing the prototype system and testing, we verified that the proposed algorithm can solve the high time delay, jitter and discontinuity problems in standard TCP protocol when transmitting voice data packets, which caused by its error control and retransmission mechanism. We proved that the method proposed in this paper is effective and practical.展开更多
文摘Objective:To discuss the current clinical application and usefulness,shortcomings and future directions of traditional and artificial intelligence(AI)-driven acoustic assessment techniques to detect voice dysfunction.Data Sources:Literature review.Conclusion:AI-based acoustic voice analysis techniques have huge potential to improve the early recognition,diagnosis,and tracking of treatment success in patients with voice disorders or diseases affecting voice function.Through smartphones,wearable devices,and server-based solutions,acoustic voice assessment techniques have become widely available and may be extended to workplace and private settings.However,the transformative potential is thwarted by several limitations including a lack of(a)consistent data collection and reporting standards,leading to heterogeneity of current databases and literature;(b)characterization what acoustic analysis techniques including AI can detect or track reliably,and whether the derived outcomes serve as a reliable marker of dysfunction,pathology,or an improvement thereof;(c)clinical validation studies in unselected patients;and(d)ethical and legal controversies.Thus,substantial effort to research,define and establish guidelines for the collection,storage,and processing of acoustic data and valid clinical applications is warranted to designsensible strategies for analysis and use.
基金funded by the National Institute of Neurological Disorders and Stroke(R01NS088160)National Institute on Deafness and Other Communication Disorders(P50DC01990,R01DC011805)。
文摘Neurological voice disorders,such as Parkinson's disease,laryngeal dystonia,and stroke-induced dysarthria,significantly impact speech production and communication.Traditional diagnostic methods rely on subjective assessment,whereas artificial intelligence(AI)offers objective,noninvasive,and scalable solutions for voice analysis.This review examines the applications,advancements,challenges,and future prospects of AI-driven methods in diagnosing,monitoring,and treating neurological voice disorders.We analyze recent advances in AI-based voice analysis,including machine learning,deep learning and signal processing techniques,and evaluate their effectiveness based on existing literature.AI models have demonstrated high accuracy in detecting subtle voice impairments,enabling early diagnosis of voice disorders,and predicting treatment response.Deep learning methods,particularly convolutional and transformer-based networks,have been effective in extracting meaningful biomarkers from acoustic or other modality data.Despite these promising advances,challenges remain,including limited high-quality data sets on some rare neurological voice disorders,ethical concerns regarding patient privacy,and the need for broad clinical validation.Further research should focus on developing standardized data sets,improving the ability of the AI model to learn representations,and enhancing its generalizability.With further development,AI-driven data analysis has the potential to transform the early detection and management of neurological voice disorders.
基金supported by the National Natural Science Foundation of China: Research on Differentially Private Frequent Pattern Miningthe National Natural Science Foundation of China: Research on Optical Transport Network Integrated Protection Strategy and Method for High-Speed Railway
文摘As the widespread employment of firewalls on the Internet, user datagram protocol（UDP） based voice over Internet protocol（Vo IP） system will be unable to transmit voice data. This paper proposed a novel method to transmit voice data based on transmission control protocol（TCP）. The method adopts a disorder TCP transmission strategy, which allows discontinuous data packets in TCP queues read by application layer directly without waiting for the retransmission of lost data packets. A byte stream data boundary identification algorithm based on consistent overhead byte stuffing algorithm is designed to efficiently identify complete voice data packets from disordered TCP packets arrived so as to transmit the data to the audio processing module timely. Then, by implementing the prototype system and testing, we verified that the proposed algorithm can solve the high time delay, jitter and discontinuity problems in standard TCP protocol when transmitting voice data packets, which caused by its error control and retransmission mechanism. We proved that the method proposed in this paper is effective and practical.
