Non-negative matrix factorization improves the efficiency of recording frequency-following responses in normal-hearing adults and neonates

One challenge in extracting the scalp-recorded frequency-following response (FFR) is related to its inherently small amplitude, which means that the response cannot be identified with confidence when only a relatively small number of recording sweeps are included in the averaging procedure. This study examined how the non-negative matrix factorisation (NMF) algorithm with a source separation constraint could be applied to improve the efficiency of FFR recordings. Conventional FFRs elicited by an English vowel/i/with a rising frequency contour were collected. <i>Study sample</i>: Fifteen normal-hearing adults and 15 normal-hearing neonates were recruited. The improvements of FFR recordings, defined as the correlation coefficient and root-mean-square differences across a sweep series of amplitude spectrograms before and after the application of the source separation NMF (SSNMF) algorithm, were characterised through an exponential curve fitting model. Statistical analysis of variance indicated that the SSNMF algorithm was able to enhance the FFRs recorded in both groups of participants. Such improvements enabled FFR extractions in a relatively small number of recording sweeps, and opened a new window to better understand how speech sounds are processed in the human brain.

头皮记录频率跟随反应（frequency-following response, FFR）的提取面临的核心挑战之一，源于其固有振幅微弱：当平均叠加程序中仅纳入少量记录扫次时，无法可靠识别该诱发电位。本研究探讨了带有源分离约束的非负矩阵分解（non-negative matrix factorization, NMF）算法在提升FFR记录效率中的应用路径。本研究采集了由带有频率上升轮廓的英语元音/i/诱发的常规FFR信号。*研究样本*：招募15名听力正常成年人与15名听力正常新生儿作为受试对象。通过指数曲线拟合模型，以源分离约束非负矩阵分解（source separation NMF, SSNMF）算法应用前后，振幅频谱图扫查序列的相关系数与均方根差值作为评价指标，表征FFR记录的改善效果。方差分析结果表明，SSNMF算法可有效增强两组受试者的FFR记录信号。该算法的性能提升使得仅通过少量记录扫次即可完成FFR提取，为深入解析人类大脑对语音的神经加工机制开辟了全新视角。