arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1107.0076stat.APcs.SD
收藏

KARMA:基于卡尔曼的自回归移动平均建模和共振峰和反共振峰跟踪推理

KARMA: Kalman-based autoregressive moving average modeling and inference for formant and antiformant tracking

Center for Laryngeal Surgery and Voice Rehabilitation, Massachusetts General Hospital(马萨诸塞州总医院喉外科与声音康复中心);Harvard University(哈佛大学);Massachusetts Institute of Technology(麻省理工学院);School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院)

Daryush D. Mehta, Daniel Rudoy, Patrick J. Wolfe

摘要:

声学语音信号中的声道共振特性被经典地跟踪,使用共振峰频率的逐帧点估计,随后使用最小化ad hoc成本函数的动态规划方法进行候选者选择和平滑。目前工作的目标是提供点估计和相关的中心频率和带宽的不确定性在统计原则的状态空间框架。扩展卡尔曼(K)算法利用线性化映射从自回归移动平均(ARMA)倒谱系数的基于帧的估计来推断共振峰和反共振峰参数。KARMA,WaveSurfer和Praat的错误分析是在全极点的情况下使用手动标记的共振峰数据库和合成的语音波形完成的。KARMA共振峰跟踪相对于两个基准算法表现出较低的整体均方根误差,第三共振峰跟踪更具挑战性。合成和口语鼻音音素的KARMA的原型跟踪性能说明。同时跟踪不确定性水平使从业者能够识别感兴趣的参数的时变置信度,并相应地调整算法设置。

英文摘要:

Vocal tract resonance characteristics in acoustic speech signals are classically tracked using frame-by-frame point estimates of formant frequencies followed by candidate selection and smoothing using dynamic programming methods that minimize ad hoc cost functions. The goal of the current work is to provide both point estimates and associated uncertainties of center frequencies and bandwidths in a statistically principled state-space framework. Extended Kalman (K) algorithms take advantage of a linearized mapping to infer formant and antiformant parameters from frame-based estimates of autoregressive moving average (ARMA) cepstral coefficients. Error analysis of KARMA, WaveSurfer, and Praat is accomplished in the all-pole case using a manually marked formant database and synthesized speech waveforms. KARMA formant tracks exhibit lower overall root-mean-square error relative to the two benchmark algorithms, with third formant tracking more challenging. Antiformant tracking performance of KARMA is illustrated using synthesized and spoken nasal phonemes. The simultaneous tracking of uncertainty levels enables practitioners to recognize time-varying confidence in parameters of interest and adjust algorithmic settings accordingly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑