Intel Corporation

Siemens Aktiengesellschaft

Svox Ag

Joachim Hofer

Georg Stemmer

Tobias Bocklet

Josef G Bauer

Piotr Rozen

Munir Nikolai Alexander Georges

Munir Georges

Josef Bauer

Da-Ming Chiang

David Pearce

Piotr Majcher

Andrzej Mialkowski

Sebastian Czyryba

Tomasz Szmelczynski

Lukasz M Malinowski

Lutz Leutelt

David J Trawick

Methods, apparatus, systems and articles of manufacture for recognizing speech are disclosed. An example system includes one or more processors to execute instructions to: identify a plurality of phonemes in a speech signal; perform a comparison of a subset of the phonemes to a phonetic string, the phonetic string representative of at least a portion of a wake up phrase; determine if one or more of the phonemes of the subset correspond to the wake up phrase based on the comparison; and generate a hypothesis of a command included in the speech signal by excluding the wake up phrase when one or more of the phonemes of the subset correspond to the wake up phrase or a portion of the wake up phrase.

Automatic speech recognition with filler model processing

A system, article, and method of automatic speech recognition with highly efficient decoding is accomplished by frequent beam width adjustment.

Method and system of automatic speech recognition with highly efficient decoding

An automatic speech recognition (ASR) system includes a memory configured to store a filler model. The filler model includes one or more phonetic strings corresponding to one or more portions of a wake up phrase. The ASR system also includes one or more processors operatively coupled to the memory and configured to analyze a speech signal with the filler model to determine whether the speech signal includes the wake up phrase or any portion of the wake up phrase. The one or more processors are also configured to generate, based on the analysis, a hypothesis of underlying speech included in the speech signal. The hypothesis excludes the wake up phrase or any portion of the wake up phrase included in the speech signal.

A mechanism is described for facilitating continuous topic detection and adaption in audio environments, according to one embodiment. A method of embodiments, as described herein, includes detecting a term relating to a topic in an audio input received from one or more microphones of the computing device including a voice-enabled device; analyzing the term based on the topic to determine an action to be performed by the computing device; and triggering an event to facilitate the computing device to perform the action consistent with the term and the topic.

Continuous topic detection and adaption in audio environments

Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include updating a start state based rejection model and a key phrase model based on scores of sub-phonetic units from an acoustic model to generate a rejection likelihood score and a key phrase likelihood score and determining whether received audio input is associated with a predetermined key phrase based on the rejection likelihood score and the key phrase likelihood score.

Low resource key phrase detection for wake on voice

Techniques are provided for wake-on-voice (WOV) key-phrase enrollment. A methodology implementing the techniques according to an embodiment includes generating a WOV key-phrase model based on identification of the sequence of sub-phonetic units of a user-provided key-phrase. The WOV key-phrase model is employed by a WOV processor for detection of the user spoken key-phrase and triggering operation of an automatic speech recognition (ASR) processor in response to the detection. The method further includes updating an ASR language model based on the user-provided key-phrase. The update includes one of embedding the WOV key-phrase model into the ASR language model, converting sub-phonetic units of the WOV key-phrase model and embedding the converted WOV key-phrase model into the ASR language model, or generating an ASR key-phrase model by applying a phoneme-syllable based statistical language model to the user-provided key-phrase and embedding the generated ASR key-phrase model into the ASR language model.

Dynamic enrollment of user-defined wake-up key-phrase for speech enabled computer system

Techniques are provided for reducing the latency of automatic speech recognition using hypothesis score trend analysis. A methodology implementing the techniques according to an embodiment includes generating complete-phrase hypotheses and partial-phrase hypotheses, along with associated likelihood scores, based on a segment of speech. The method also includes selecting the complete-phrase hypothesis associated with the highest of the complete-phrase hypotheses likelihood scores, and selecting the partial-phrase hypothesis associated with the highest of the partial-phrase hypotheses likelihood scores. The method further includes calculating a relative likelihood score based on a ratio of the likelihood score associated with the selected complete-phrase hypothesis to the likelihood score associated with the selected partial-phrase hypothesis. The method further includes calculating a trend of the relative likelihood score as a function of time and identifying an endpoint of the speech based on a determination that the trend does not decrease over a selected time period.

Score trend analysis for reduced latency automatic speech recognition

A system, article, and method include techniques of automatic speech recognition using posterior confidence scores.

Method and system of automatic speech recognition using posterior confidence scores

An embodiment of a speech endpoint detector apparatus may include a speech detector to detect a presence of speech in an electronic speech signal, a pause duration measurer communicatively coupled to the speech detector to measure a duration of a pause following a period of detected speech, an end of utterance detector communicatively coupled to the pause duration measurer to detect if the pause measured following the period of detected speech is greater than a pause threshold corresponding to an end of an utterance, and a pause threshold adjuster to adaptively adjust the pause threshold corresponding to an end of an utterance based on stored pause information. Other embodiments are disclosed and claimed.

Adaptive speech endpoint detector

Techniques are provided for calculating reset parameters for recurrent neural networks (RNN). A methodology implementing the techniques according to an embodiment includes generating a sequence of statistics. The calculation of each statistic is based on outputs of an RNN that is periodically re-initialized at a selected RNN reset time such that each of the calculated statistics is associated with a unique RNN reset time selected from a pre-determined range of reset times. The method further includes analyzing the sequence to identify a maximum interval during which the sequence remains relatively constant. The method further includes selecting a reset time parameter and reset context duration parameter, for re-initialization of the RNN during operation. The reset time parameter is based on the duration of the identified maximum interval and the reset context duration parameter is based on a time associated with the starting point of the identified maximum interval.

Statistical-analysis-based reset of recurrent neural networks for automatic speech recognition

A computer-implemented method of speech recognition comprises forming a weighted finite state transducer (WFST) having nodes associated with states and interconnected by arcs, and to identify at least one word or word sequence hypothesis, identifying multiple sub-graphs on the WFST, each sub-graph having the same arrangement of multiple states and at least one arc, and propagating tokens in parallel through the sub-graphs, where each sub-graph is stored as a supertoken each having an array of tokens.

System and method of automatic speech recognition using parallel processing for weighted finite state transducer-based speech decoding

A method for context-aware query recognition in an electronic device includes receiving user speech from an input device. A speech signal is generated from the user speech. It is determined if the speech signal includes an action to be performed and if the electronic device is the intended recipient of the user speech. If the recognized speech signal include the action and the intended recipient of the user speech is the electronic device, a command is generated for the electronic device to perform the action.

Context-aware query recognition for electronic devices

A method in a computing device for decoding a weighted finite state transducer (WFST) for automatic speech recognition is described. The method includes sorting a set of one or more WFST arcs based on their arc weight in ascending order. The method further includes iterating through each arc in the sorted set of arcs according to the ascending order until the score of the generated token corresponding to an arc exceeds a score threshold. The method further includes discarding any remaining arcs in the set of arcs that have yet to be considered.

Growing community of inventors

Munich, Germany

Joachim Hofer