Abstract: Linear approximation of the background noise is applied after feature extraction and prior to speaker adaptation to allow the speaker adaptation system to adapt the speech models to the enrolling user without distortion from background noise. The linear approximation is applied in the feature domain, such as in the cepstral domain. Any adaptation technique that is commutative in the feature domain may be used.

Abstract: An embedded device for playing media files is capable of generating a play list of media files based on input speech from a user. It includes an indexer generating a plurality of speech recognition grammars. According to one aspect of the invention, the indexer generates speech recognition grammars based on contents of a media file header of the media file. According to another aspect of the invention, the indexer generates speech recognition grammars based on categories in a file path for retrieving the media file to a user location. When a speech recognizer receives an input speech from a user while in a selection mode, a media file selector compares the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

Abstract: A voice-tag editor develops voice-tag “sounds like” pairs for a voice-tagging lexicon. The voice-tag editor is receptive of alphanumeric characters input by a user. The alphanumeric characters are indicative of a voice tag and/or “sounds like” text. The voice-tag editor is configured to allow the user to view and edit the alphanumeric characters. A text parser connected to the voice-tag editor generates normalized text corresponding to the “sounds like” text. The normalized text serves as recognition text for the voice tag and is displayed by the voice-tag editor. A storage mechanism is connected to the editor. The storage mechanism updates the lexicon with the alphanumeric characters which represent voice-tag “sounds like” pairs.

Abstract: In one aspect, the present invention provides a method for detecting speech end points in an input signal containing speech portions and non-speech (noise) portions. The method includes processing signal frames of a digital input signal containing speech and non-speech portions to extract features from the signal frames, comparing at least one property of the processed signal frames to a noise model and a speech model to determine whether a processed signal frame contains speech or noise, generating a signal indicative of the speech or noise determination, and updating either the speech model or the noise model depending upon whether a processed signal frame is determined to contain speech or noise, respectively. In some configurations, the method also includes resetting the speech and noise models dependent upon whether a number of zero crossings in a determined inter-frame correlation is greater than a threshold number.

Abstract: An embedded device for playing media files is capable of generating a play list of media files based on input speech from a user. It includes an indexer generating a plurality of speech recognition grammars. According to one aspect of the invention, the indexer generates speech recognition grammars based on contents of a media file header of the media file. According to another aspect of the invention, the indexer generates speech recognition grammars based on categories in a file path for retrieving the media file to a user location. When a speech recognizer receives an input speech from a user while in a selection mode, a media file selector compares the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

Abstract: Linear approximation of the background noise is applied after feature extraction and prior to speaker adaptation to allow the speaker adaptation system to adapt the speech models to the enrolling user without distortion from background noise. The linear approximation is applied in the feature domain, such as in the cepstral domain. Any adaptation technique that is commutative in the feature domain may be used.

Abstract: The acoustic speech signal is decomposed into wavelets arranged in an asymmetrical tree data structure from which individual nodes may be selected to best extract local features, as needed to model specific classes of sound units. The wavelet packet transformation is smoothed through integration and compressed to apply a non-linearity prior to discrete cosine transformation. The resulting subband features such as cepstral coefficients may then be used to construct the speech recognizer's speech models. Using the local feature information extracted in this manner allows a single recognizer to be optimized for several different classes of sound units, thereby eliminating the need for parallel path recognizers.