Speech formant trajectory estimation using dynamic programming with modulated transition costs
Speech formant trajectory estimation using dynamic programming with modulated transition costs
复制标题
使用具有调制转换成本的动态规划进行语音共振峰轨迹估计
DOI：
10.1121/1.2024869
复制
发表时间：
1987
影响因子：
2.4
通讯作者：
D. Talkin
中科院分区：
文献类型：
--
作者：
D. Talkin
一种自动跟踪语音共振峰频率的新算法已经开发出来。动态规划用于通过施加适当的频率连续性约束来优化共振峰轨迹估计。连续性约束由平稳性函数调节。共振峰频率是从通过求解根据语音波形定期计算的线性预测多项式的根而提出的候选频率中选择的。根据每个映射的分量共振峰的频率和带宽，在每个帧计算复数根到共振峰频率的所有可能映射的局部成本。然后使用修改的维特比算法将这些映射中的每一个与前一帧中的每一个映射连接的成本最小化。对 88 名男性和 43 名女性所说的两句话进行了分析。在超过 80% 的句子中，所有发音区域的前三个共振峰均被正确跟踪。这些性能结果基于光谱分析...
A new algorithm to track automatically speech formant frequencies have been developed. Dynamic programming is used to optimize formant trajectory estimates by imposing appropriate frequency continuity constraints. The continuity constraints are modulated by a stationarity function. The formant frequencies are selected from candidates proposed by solving for the roots of the linear predictor polynomial computed periodically from the speech waveform. The local costs of all possible mappings of the complex roots to formant frequencies are computed at each frame based on the frequencies and bandwidths of the component formants for each mapping. The cost of connecting each of these mappings with each of the mappings in the previous frame is then minimized using a modified Viterbi algorithm. Two sentences spoken by 88 males and 43 females were analyzed. The first three formants were tracked correctly in all sonorant regions in over 80% of the sentences. These performance results are based on spectrographic anal...