Abstract: Acoustic features are batched into two different batches. The second batch of the two batches is made in response to a detection of a word hypothesis output by a speech recognition network that received the first batch. The number of acoustic feature frames of the second batch is equal to a second batch size greater than the first batch size. The second batch is also to the speech recognition network for processing.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: Embodiments may include collection of a first batch of acoustic feature frames of an audio signal, the number of acoustic feature frames of the first batch equal to a first batch size, input of the first batch to a speech recognition network, collection, in response to detection of a word hypothesis output by the speech recognition network, of a second batch of acoustic feature frames of the audio signal, the number of acoustic feature frames of the second batch equal to a second batch size greater than the first batch size, and input of the second batch to the speech recognition network.

Abstract: The described technology provides arbitration between speech recognition results generated by different automatic speech recognition (ASR) engines, such as ASR engines trained according to different language or acoustic models. The system includes an arbitrator that selects between a first speech recognition result representing an acoustic utterance as transcribed by a first ASR engine and a second speech recognition result representing the acoustic utterance as transcribed by a second ASR engine. This selection is based on a set of confidence features that is initially used by the first ASR engine or the second ASR engine to generate the first and second speech recognition results.

Abstract: The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as accent origins (e.g. native, non-native), speech channels (e.g. mobile, bluetooth, desktop etc.), speech application scenario (e.g. voice search, short message dictation etc.), and speaker variation (e.g. individual speakers or clustered speakers), etc. The technology described herein uses certain sub-modules in a first context and a second group of sub-modules in a second context.

Abstract: Air filtration media and methods of processing the same are described herein. One method of processing an air filtration medium includes mixing an adsorption material, a polymer material, and a reinforcement material, compressing the mixture, and heating the mixture.

Abstract: A computer-readable speaker-adapted speech engine acoustic model can be generated. The generating of the acoustic model can include performing speaker-specific adaptation of one or more layers of the model to produce one or more adaptive layers comprising layer weights, with the speaker-specific adaptation comprising a data size reduction technique. The data size reduction technique can be threshold value adaptation, corner area adaptation, diagonal-based quantization, adaptive matrix reduction, or a combination of these reduction techniques. The speaker-adapted speech engine model can be accessed and used in performing speech recognition on computer-readable audio speech input via a computerized speech recognition engine.

Abstract: The described technology provides normalization of speech recognition confidence classifier (CC) scores that maintains the accuracy of acceptance metrics. A speech recognition CC scores quantitatively represents the correctness of decoded utterances in a defined range (e.g., [0,1]). An operating threshold is associated with a confidence classifier, such that utterance recognitions having scores exceeding the operating threshold are deemed acceptable. However, when a speech recognition engine, an acoustic model, and/or other parameters are updated by the platform, the correct-accept (CA) versus false-accept (FA) profile can change such that the application software's operating threshold is no longer valid or as accurate.

Abstract: The technology described herein uses a modular model to process speech. A deep learning based acoustic model comprises a stack of different types of neural network layers. The sub-modules of a deep learning based acoustic model can be used to represent distinct non-phonetic acoustic factors, such as accent origins (e.g. native, non-native), speech channels (e.g. mobile, bluetooth, desktop etc.), speech application scenario (e.g. voice search, short message dictation etc.), and speaker variation (e.g. individual speakers or clustered speakers), etc. The technology described herein uses certain sub-modules in a first context and a second group of sub-modules in a second context.

Abstract: The described technology provides arbitration between speech recognition results generated by different automatic speech recognition (ASR) engines, such as ASR engines trained according to different language or acoustic models. The system includes an arbitrator that selects between a first speech recognition result representing an acoustic utterance as transcribed by a first ASR engine and a second speech recognition result representing the acoustic utterance as transcribed by a second ASR engine. This selection is based on a set of confidence features that is initially used by the first ASR engine or the second ASR engine to generate the first and second speech recognition results.

Abstract: The described technology provides normalization of speech recognition confidence classifier (CC) scores that maintains the accuracy of acceptance metrics. A speech recognition CC scores quantitatively represents the correctness of decoded utterances in a defined range (e.g., [0,1]). An operating threshold is associated with a confidence classifier, such that utterance recognitions having scores exceeding the operating threshold are deemed acceptable. However, when a speech recognition engine, an acoustic model, and/or other parameters are updated by the platform, the correct-accept (CA) versus false-accept (FA) profile can change such that the application software's operating threshold is no longer valid or as accurate.

Abstract: Aspects of the technology described herein relate to a new type of deep neural network (DNN). The new DNN is described herein as a deep neural support vector machine (DNSVM). Traditional DNNs use the multinomial logistic regression (softmax activation) at the top layer and underlying layers for training. The new DNN instead uses a support vector machine (SVM) as one or more layers, including the top layer. The technology described herein can use one of two training algorithms to train the DNSVM to learn parameters of SVM and DNN in the maximum-margin criteria. The first training method is a frame-level training. In the frame-level training, the new model is shown to be related to the multi-class SVM with DNN features. The second training method is the sequence-level training. The sequence-level training is related to the structured SVM with DNN features and HMM state transition features.

Abstract: Techniques and systems for training an acoustic model are described. In an embodiment, a technique for training an acoustic model includes dividing a corpus of training data that includes transcription errors into N parts, and on each part, decoding an utterance with an incremental acoustic model and an incremental language model to produce a decoded transcription. The technique may further include inserting silence between a pair of words into the decoded transcription and aligning an original transcription corresponding to the utterance with the decoded transcription according to time for each part. The technique may further include selecting a segment from the utterance having at least Q contiguous matching aligned words, and training the incremental acoustic model with the selected segment. The trained incremental acoustic model may then be used on a subsequent part of the training data. Other embodiments are described and claimed.

Abstract: Techniques for enhanced automatic speech recognition are described. An enhanced ASR system may be operative to generate an error correction function. The error correction function may represent a mapping between a supervised set of parameters and an unsupervised training set of parameters generated using a same set of acoustic training data, and apply the error correction function to an unsupervised testing set of parameters to form a corrected set of parameters used to perform speaker adaptation. Other embodiments are described and claimed.

Abstract: Disclosed is an interrupt dispatching system and method in a multi-core processor environment. The processor includes an interrupt dispatcher and N cores capable of interrupt handling which are divided into a plurality of groups of cores, where N is a positive integer greater than one. The method generates a token in response to an arriving interrupt; determines a group of cores to be preferentially used to handle the interrupt as a hot group in accordance with the interrupt; and sends the token to the hot group, determines sequentially from the first core in the hot group whether an interrupt dispatch termination condition is satisfied, and determines the current core as a response core to be used to handle the interrupt upon determining satisfaction of the interrupt dispatch termination condition. With the invention, delay in responding to an interrupt by the processor is reduced providing optimized performance of the processor.

Abstract: Techniques and systems for training an acoustic model are described. In an embodiment, a technique for training an acoustic model includes dividing a corpus of training data that includes transcription errors into N parts, and on each part, decoding an utterance with an incremental acoustic model and an incremental language model to produce a decoded transcription. The technique may further include inserting silence between a pair of words into the decoded transcription and aligning an original transcription corresponding to the utterance with the decoded transcription according to time for each part. The technique may further include selecting a segment from the utterance having at least Q contiguous matching aligned words, and training the incremental acoustic model with the selected segment. The trained incremental acoustic model may then be used on a subsequent part of the training data. Other embodiments are described and claimed.

Abstract: Techniques for enhanced automatic speech recognition are described. An enhanced ASR system may be operative to generate an error correction function. The error correction function may represent a mapping between a supervised set of parameters and an unsupervised training set of parameters generated using a same set of acoustic training data, and apply the error correction function to an unsupervised testing set of parameters to form a corrected set of parameters used to perform speaker adaptation. Other embodiments are described and claimed.

Abstract: Disclosed is an interrupt dispatching system and method in a multi-core processor environment. The processor includes an interrupt dispatcher and N cores capable of interrupt handling which are divided into a plurality of groups of cores, where N is a positive integer greater than one. The method generates a token in response to an arriving interrupt; determines a group of cores to be preferentially used to handle the interrupt as a hot group in accordance with the interrupt; and sends the token to the hot group, determines sequentially from the first core in the hot group whether an interrupt dispatch termination condition is satisfied, and determines the current core as a response core to be used to handle the interrupt upon determining satisfaction of the interrupt dispatch termination condition. With the invention, delay in responding to an interrupt by the processor is reduced providing optimized performance of the processor.

Abstract: A graphic user interface system for use with a content based retrieval system includes an active display having display areas. For example, the display areas include a main area providing an overview of database contents by displaying representative samples of the database contents. The display areas also include one or more query areas into which one or more of the representative samples can be moved from the main area by a user employing gesture based interaction. A query formulation module employs the one or more representative samples moved into the query area to provide feedback to the content based retrieval system.