Duanpei Wu

System and method for speech verification using out-of-vocabulary models

A system and method for speech verification using out-of-vocabulary models includes a speech recognizer that has a model bank with system vocabulary word models, a garbage model, and one or more noise models. The model bank may reject an utterance or other sound as an invalid vocabulary word when the model bank identifies the utterance or other sound as corresponding to the garbage model or the noise models. Initial noise models may be selectively combined into a pre-determined number of final noise model clusters to effectively reduce the number of noise models that are utilized by the model bank of the speech recognizer to verify system vocabulary words.

A robust speech detection algorithm for speech activated hands-free applications

This paper describes a novel noise robust speech detection algorithm that can operate reliably in severe noisy car conditions. High performance has been obtained with the following techniques: (1) noise suppression based on principal component analysis for pre-processing, (2) robust endpoint detection using dynamic parameters, and (3) speech verification using the periodicity of voiced signals with harmonic enhancement. Noise suppression improves the SNR as compared with nonlinear spectrum subtraction by about 20 dB. This makes the endpoint detection operate reliably in SNRs down to -10 dB. In car environments, road bump noises are problematic for speech detectors causing mis-detection errors. Speech verification helps to remove these errors. This technology is being used in Sony car navigation products.

Compensation of channel and noise distortions combining normalization and speech enhancement techniques

This paper introduces two techniques to obtain robust speech recognition devices in mismatch conditions (additive noise mismatch and channel mismatch). The first algorithm, adaptive Gaussian attenuation algorithm (AGA), is a speech enhancement technique developed to reduce the effects of additive background noise in a wide range of signal noise ratio (SNR) and noise conditions. The technique is closely related to the classical noise spectral subtraction (SS) scheme, but in the proposed model the mean and variance of noise are used to better attenuate the noise. Information of the SNR is also introduced to provide adaptability at different SNR conditions. The second algorithm, cepstral mean normalization and variance-scaling technique (CMNVS), is an extension of the cepstral mean normalization (CMN) technique to provide robust features to convolutive and additive noise distortions. The requirements of the techniques are also analyzed in the paper. Combining both techniques the relative channel distortion effects were reduced to 90% on the HTIMIT task and the relative additive noise effects were reduced to 77% using the TIMIT database mixed with car noises at different SNR conditions.