Xavier Menendez-Pidal

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.

Automatic set-up for speech recognition engines based on merit optimization

We propose an automatic method to set-up the several parameters that define the behavior and performance of a typical speech recognition engine. Such parameters include weights and beam widths among others. Our method is based on the definition of a merit function. Here, merit is understood as an intuitive notion of recognition performance based on both recognition accuracy and computation time. A convenient definition of merit allows an optimization procedure to be applied to define a convenient set-up for the recognizer with little human intervention. The method is applied to adjust the recognition parameters of two different LVCSR (large vocabulary continuous speech recognition) applications, one in American English and another in Japanese.

Automatic phoneme labeler in the TIMIT database

A phonetic HMM labeler was developed for use in an automatic diphone extraction system. Using the TIMIT database for training, the best HMM labeler performance was obtained when the number of states for a given phoneme model was proportional to the average duration of that phoneme over the TIMIT database, and the HMM topology allowed both repetition of states and skipping of adjacent states. The acoustic feature set was comprised of 30 features per frame (8 Mel cepstral coefficients, the log rms amplitude, and the zero crossing rate of a frame, as well as their first and second time derivatives). Labeling accuracy was tested using all speech files in the TIMIT test set and accuracy was assessed in terms of the degree of separation between labeler‐assigned phoneme boundaries and the nominal phoneme boundaries provided in the database. 97.4% of the boundaries assigned by the labeler were within 30 ms of the nominal phoneme boundaries, and 86.8% were within 10 ms (i.e., one analysis frame) of the nominal bou...