A method includes receiving acoustic features of a first utterance spoken by a first user that speaks with typical speech and processing the acoustic features of the first utterance using a general speech recognizer to generate a first transcription of the first utterance. The operations also include analyzing the first transcription of the first utterance to identify one or more bias terms in the first transcription and biasing the alternative speech recognizer on the one or more bias terms identified in the first transcription. The operations also include receiving acoustic features of a second utterance spoken by a second user that speaks with atypical speech and processing, using the alternative speech recognizer biased on the one or more terms identified in the first transcription, the acoustic features of the second utterance to generate a second transcription of the second utterance.

A method includes receiving acoustic features of a first utterance spoken by a first user that speaks with typical speech and processing the acoustic features of the first utterance using a general speech recognizer to generate a first transcription of the first utterance. The operations also include analyzing the first transcription of the first utterance to identify one or more bias terms in the first transcription and biasing the alternative speech recognizer on the one or more bias terms identified in the first transcription. The operations also include receiving acoustic features of a second utterance spoken by a second user that speaks with atypical speech and processing, using the alternative speech recognizer biased on the one or more terms identified in the first transcription, the acoustic features of the second utterance to generate a second transcription of the second utterance.

Provided are a method of generating a trained third neural network to recognize a speaker of a noisy speech signal by combining a trained first neural network which is a skip connection-based neural network for removing noise from the noisy speech signal with a trained second neural network for recognizing the speaker of a speech signal, and a neural network device for operating the neural networks.

Provided are a method of generating a trained third neural network to recognize a speaker of a noisy speech signal by combining a trained first neural network which is a skip connection-based neural network for removing noise from the noisy speech signal with a trained second neural network for recognizing the speaker of a speech signal, and a neural network device for operating the neural networks.

Technologies are generally described for systems, devices and methods effective to identify an individual. In some examples, a microphone may receive sound data such as sound that may be present in a mall. A processor, that may be in communication with the microphone, may determine a name from the sound data. Stated differently, the processor may determine that the name is part of or included in the sound data. The processor may generate a query based on the name and may send the query to a social network database. The processor may receive a response to the query from the social network database and may identify the individual based on the response.

Technologies are generally described for systems, devices and methods effective to identify an individual. In some examples, a microphone may receive sound data such as sound that may be present in a mall. A processor, that may be in communication with the microphone, may determine a name from the sound data. Stated differently, the processor may determine that the name is part of or included in the sound data. The processor may generate a query based on the name and may send the query to a social network database. The processor may receive a response to the query from the social network database and may identify the individual based on the response.

One embodiment provides a method, including receiving, at an audio capture device, a customized activation cue; identifying, using a processor, contextual information associated with a user; analyzing, using the contextual information, characteristics of the customized activation cue; identifying, based on the analyzation, a uniqueness associated with the customized activation cue; and responsive to said identifying, notifying a user that the customized activation cue has inadequate uniqueness. Other aspects are described and claimed.

A method and apparatus for processing voice data of a speech received from a speaker are provided. The method includes extracting a speaker feature vector from the voice data of the speech received from a speaker, generating a speaker feature map by positioning the extracted speaker feature vector at a specific position on a multi-dimensional vector space, forming a plurality of clusters indicating features of voices of a plurality of speakers by grouping at least one speaker feature vector positioned on the speaker feature map, and classifying the plurality of speakers according to the plurality of clusters.

Systems, devices, methods, and computer readable media are provided in various embodiments relating to generating a dynamic challenge passphrase data object. The method includes establishing, a plurality of data record clusters, representing a mutually exclusive set of structured data records of an individual, ranking the plurality of feature data fields based on a determined contribution value of each feature data field relative to the establishing of the data record cluster, and identifying, using the ranked plurality of feature data fields, a first and a second feature data field of the plurality of feature data fields. The method includes generating the dynamic challenge passphrase data object, wherein the first or the second feature data field is used to establish a statement string portion, and a remaining one of the first or the second feature data field is used to establish a question string portion and a correct response string.

Provided are a method and device for recognizing a speaker by using a resonator. The method of recognizing the speaker includes receiving a plurality of electrical signals corresponding to a speech of the speaker from a plurality of resonators having different resonance bands; obtaining a difference of magnitudes of the plurality of electrical signals; and recognizing the speaker based on the difference of magnitudes of the plurality of electrical signals.