Study on noisy speech endpoint detection method
带噪语音端点检测方法研究

A major factor influencing the capability of speech recognition systems is the accuracy of endpoint detection, Some good detection algorithms cannot take effect in practical use because small SNR reduces the recognition rate. An algorithm for speech endpoint detection based on time-frequency-variance-summation was proposed. The experiments prove that it has better detection capability with low SNR compared with other three endpoint detection algorithms.