Speaking fundamental frequency characteristics as a function of age and professional singing

The purposes of this project were to discover (1) if the speaking fundamental frequency (SFF) levels of professional singers differ significantly from those of nonsingers and (2) if the age-related SFF patterns are similar for these two classes of individuals. Sixty professional singers and 94 nonsingers were recorded reading the first paragraph of the “Rainbow Passage;” both males and females were included. Three paired groups (young, middle, and old age) were studied; they were selected on the basis of health and age. The professional singer groups were further divided by a binary voice classification system, specifically that of soprano/alto for women and tenor/baritone for men. It was found that the sopranos and tenors exhibited significantly higher SFF levels then did the age-matched nonsingers, whereas the altos and baritones did not differ significantly from the controls. Relationships within the performer groups were mixed. For example, there appeared to be a systemic trend for the sopranos and tenors to exhibit higher SFF levels than the altos and baritones. Finally, although the nonsinger SFF levels varied significantly as a function of age, those for the professional singers did not.     

A Robust, Real-Time Voice Activity Detection Algorithm for Embedded Mobile Devices

When an Automatic Speech Recognition (ASR) system is applied in noisy environments, Voice Activity Detection (VAD) is crucial to the performance of the overall system. The employment of the VAD for ASR on embedded mobile systems will minimize physical distractions and make the system convenient to use. Conventional VAD algorithm is of high complexity, which makes it unsuitable for embedded mobile devices; or of low robustness, which holds back its application in mobile noisy environments. In this paper, we propose a robust VAD algorithm specifically designed for ASR on embedded mobile devices. The architecture of the proposed algorithm is based on a two-level decision making strategy, where there is an interaction between a lower features-based level and subsequent decision logic based on a finite-state machine. Many discriminating features are employed in the lower level to improve the robustness of the VAD. The two-level decision strategy allows different features to be used in different states and reduces the cost of the algorithm, which makes the proposed algorithm suitable for embedded mobile devices. The evaluation experiments show the proposed VAD algorithm is robust and contribute to the overall performance gain of the ASR system in various acoustic environments.     

一种机器人智能语音识别算法研究

针对智能机器人在非特定人语音识别中识别率偏低的问题,提出了一种双门限的端点检测算法,精确地检测出了语音端点,对分形维数和Mel频率倒谱系数(MFCC)进行结合,同时基于隐马尔可夫(HMM)模型,提出了智能机器人命令识别系统;在实验室环境下,利用Cool Edit软件录制了5男5女的语音,采样率为8 kHz,精度为16位,内容为5个命令词,每个词均被采集6次,将每人的前3次发音作为模板语音,后3次发音作为测试语音,实验结果表明,系统识别率可以达到85%以上,MFCC与分形维数混合的语音特征参数的算法提高了系统识别率,优化了系统性能;该方法用于非特定人语音智能识别是可行的、有效的。     

Boot Camp: A Novel Intensive Approach to Voice Therapy

It is well known in the disciplines of neurobiology, exercise physiology, motor learning, and psychotherapy that desirable learning and behavior changes occur primarily from practice that involves high-intensity overload, variability, and specificity of training. We propose a novel treatment approach called intensive short-term voice therapy that uses these practice parameters for recalcitrant dysphonia. Intensive short-term voice therapy involves multiple sessions with a variety of clinicians, incorporating multiple simultaneous therapeutic approaches. The intensive short-term voice therapy approach is characterized by voice therapy for 1–4 successive days each with an average of 5 hours of therapy and five clinicians. This form of intensive voice therapy provides rigorous practice, involving not only overload but also opportunities for specificity and individuality thereby facilitating better transfer of learned skills. This article discusses the conceptual, theoretical, and practical foundations of this novel therapy approach.     

以虚拟仪器为平台的声学实验

基于计算机声卡和Adobe Audition软件制作了声学虚拟仪器,可实现示波器、信号发生器和频率计算仪器功能,并介绍了此声学虚拟仪器在双音多频信号DTMF的研究、声速的测量和变音钟实验中的具体应用.     

应用ResNet和CatBoost检测重放语声*

针对短语声指令声频信息少、不适用句子级重放语声检测的问题以及近距离录声后用高质量重放设备重放的语声难以检测的问题，提出了一种适用于词级重放语声检测的模型。首先，利用短时傅里叶变换、低频平均能量计算和帧排序等方法选择声频帧，然后提取这些帧的伽马通频率倒谱系数。其次，用基于自注意机制的残差网络模型进一步提取伽马通频率倒谱系数中的信息，并转化为特征向量。最后，将提取后的特征向量用CatBoost分类，从而提高检测性能。在POCO数据集上的实验结果表明，提出的方法可以以87.54%的准确率和12.53%的等错误率检测重放语声，优于基线和现有的方法。该文提出的方法在ASVspoof2019 PA数据集上的等错误率与串联检测代价函数分别为4.92%和0.1418，证明该文方法也适用于多种设置的重放语声检测。