At&t Intellectual Property I, L.p.

Nuance Communications, Inc.

Vincent Goffin

Andrej Ljolje

Murat Saraclar

Mazin E Gilbert

Taniya Mishra

Diamantino Antonio Caseiro

Sarangarajan Parthasarathy

Michael Dennis Riley

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for assigning saliency weights to words of an ASR model. The saliency values assigned to words within an ASR model are based on human perception judgments of previous transcripts. These saliency values are applied as weights to modify an ASR model such that the results of the weighted ASR model in converting a spoken document to a transcript provide a more accurate and useful transcription to the user.

System and method for optimizing speech recognition and natural language parameters with user feedback

A method and system for training an automatic speech recognition system are provided. The method includes separating training data into speaker specific segments, and for each speaker specific segment, performing the following acts: generating spectral data, selecting a first warping factor and warping the spectral data, and comparing the warped spectral data with a speech model. The method also includes iteratively performing the steps of selecting another warping factor and generating another warped spectral data, comparing the other warped spectral data with the speech model, and if the other warping factor produces a closer match to the speech model, saving the other warping factor as the best warping factor for the speaker specific segment. The system includes modules configured to control a processor in the system to perform the steps of the method.

Low latency real-time vocal tract length normalization

A method, system and machine-readable medium are provided. Speech input is received at a speech recognition component and recognized output is produced. A common dialog cue from the received speech input or input from a second source is recognized. An action is performed corresponding to the recognized common dialog cue. The performed action includes sending a communication from the speech recognition component to the speech generation component while bypassing a dialog component.

System and method for isolating and processing common dialog cues

Systems and methods for low-latency real-time speech recognition/transcription. A discriminative feature extraction, such as a heteroscedastic discriminant analysis transform, in combination with a maximum likelihood linear transform is applied during front-end processing of a digital speech signal. The extracted features reduce the word error rate. A discriminative acoustic model is applied by generating state-level lattices using Maximum Mutual Information Estimation. Recognition networks of language models are replaced by their closure. Latency is reduced by eliminating segmentation such that a number of words/sentences can be recognized as a single utterance. Latency is further reduced by performing front-end normalization in a causal fashion.

Low latency real-time speech transcription

A method and apparatus for performing speech recognition are provided. A Vocal Tract Length Normalized acoustic model for a speaker is generated from training data. Speech recognition is performed on a first recognition input to determine a first best hypothesis. A first Vocal Tract Length Normalization factor is estimated based on the first best hypothesis. Speech recognition is performed on a second recognition input using the Vocal Tract Length Normalized acoustic model to determine an other best hypothesis. An other Vocal Tract Length Normalization factor is estimated based on the other best hypothesis and at least one previous best hypothesis.

Growing community of inventors

Summit, NJ, United States of America

Vincent Goffin