| Robust Speech Recognition Using a Harmonic Model |
| |
| 作者姓名： | 许超 曹志刚 |
| |
| 作者单位： | DepartmentofElectronicEngineering,TsinghuaUniversity,Beijing100084,China |
| |
| 基金项目： | Supported by the National Natural Science Foundation of China (No. 60072011) |
| |
| 摘 要： | Automatic speech recognition under conditions of a noisy environment remains a challenging problem. Traditionally, methods focused on noise structure, such as spectral subtraction, have been employed to address this problem, and thus the performance of such methods depends on the accuracy in noise estimation. In this paper, an alternative method, using a harmonic-based spectral reconstruction algorithm, is proposed for the enhancement of robust automatic speech recognition. Neither noise estimation nor noise-model training are required in the proposed approach. A spectral subtraction integrated autocorrelation function is proposed to determine the pitch for the harmonic model. Recognition results show that the harmonic-based spectral reconstruction approach outperforms spectral subtraction in the middle- and lowsignal noise ratio (SNR) ranges. The advantage of the proposed method is more manifest for non-stationary noise, as the algorithm does not require an assumption of stationary noise.
|
| 关 键 词： | 健壮语音识别 语音增强 谐波模型 噪声估计 光谱重建 |
Robust Speech Recognition Using a Harmonic Model |
| |
| XU Chao,CAO Zhigang.Robust Speech Recognition Using a Harmonic Model[J].Tsinghua Science and Technology,2004,9(2):202-206. |
| |
| Authors: | XU Chao CAO Zhigang |
| |
| Institution: | XU Chao,CAO Zhigang Department of Electronic Engineering,Tsinghua University,Beijing 100084,China |
| |
| Abstract: | Automatic speech recognition under conditions of a noisy environment remains a challenging problem. Traditionally, methods focused on noise structure, such as spectral subtraction, have been em-ployed to address this problem, and thus the performance of such methods depends on the accuracy in noise estimation. In this paper, an alternative method, using a harmonic-based spectral reconstruction algo-rithm, is proposed for the enhancement of robust automatic speech recognition. Neither noise estimation nor noise-model training are required in the proposed approach. A spectral subtraction integrated autocorrela-tion function is proposed to determine the pitch for the harmonic model. Recognition results show that the harmonic-based spectral reconstruction approach outperforms spectral subtraction in the middle- and low-signal noise ratio (SNR) ranges. The advantage of the proposed method is more manifest for non-stationary noise, as the algorithm does not require an assumption of stationary noise. |
| |
| Keywords: | robust speech recognition speech enhancement pitch extraction harmonic model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
