Spectral Reconstruction and Noise Model Estimation Based on a Masking Model for Noise Robust Speech Recognition
作者: Jose A. GonzalezAngel M. GómezAntonio M. PeinadoNing MaJon Barker
作者单位: 1University of Sheffield
2Telematics and Communications
刊名: Circuits, Systems, and Signal Processing, 2017, Vol.36 (9), pp.3731-3760
来源数据库: Springer Nature Journal
DOI: 10.1007/s00034-016-0480-7
关键词: Speech recognitionNoise robustnessFeature compensationNoise model estimationMissing data imputation
英文摘要: An effective way to increase noise robustness in automatic speech recognition (ASR) systems is feature enhancement based on an analytical distortion model that describes the effects of noise on the speech features. One of such distortion models that has been reported to achieve a good trade-off between accuracy and simplicity is the masking model. Under this model, speech distortion caused by environmental noise is seen as a spectral mask and, as a result, noisy speech features can be either reliable (speech is not masked by noise) or unreliable (speech is masked). In this paper, we present a detailed overview of this model and its applications to noise robust ASR. Firstly, using the masking model, we derive a spectral reconstruction technique aimed at enhancing the noisy speech features....
原始语种摘要: An effective way to increase noise robustness in automatic speech recognition (ASR) systems is feature enhancement based on an analytical distortion model that describes the effects of noise on the speech features. One of such distortion models that has been reported to achieve a good trade-off between accuracy and simplicity is the masking model. Under this model, speech distortion caused by environmental noise is seen as a spectral mask and, as a result, noisy speech features can be either reliable (speech is not masked by noise) or unreliable (speech is masked). In this paper, we present a detailed overview of this model and its applications to noise robust ASR. Firstly, using the masking model, we derive a spectral reconstruction technique aimed at enhancing the noisy speech features....
全文获取路径: Springer Nature  (合作)
分享到:
来源刊物:
影响因子:0.982 (2012)

×
关键词翻译
关键词翻译
  • Recognition 识别
  • features 特征
  • speech 演说
  • noisy 有噪声
  • robustness 坚固性
  • recognition 识别
  • masking 蒙片法
  • reconstruction 复原
  • distortion 畸变
  • noise 噪声