A speech signal processing method and a related device thereof are provided. The method may be applied to the audio field and includes: obtaining a user speech signal captured by a sensor; obtaining a corresponding vibration signal when a user generates a speech, where the vibration signal indicates a vibration feature of a body part of the user, and the body part is a part that vibrates correspondingly based on sound-making behavior when the user is making a sound; and obtaining target speech information based on the vibration signal and the user speech signal captured by the sensor. In this application, the vibration signal is used as a basis for speech recognition.

The present invention is directed to a deep neural network (DNN) having a triplet network architecture, which is suitable to perform speaker recognition. In particular, the DNN includes three feed-forward neural networks, which are trained according to a batch process utilizing a cohort set of negative training samples. After each batch of training samples is processed, the DNN may be trained according to a loss function, e.g., utilizing a cosine measure of similarity between respective samples, along with positive and negative margins, to provide a robust representation of voiceprints.

The present invention is directed to a deep neural network (DNN) having a triplet network architecture, which is suitable to perform speaker recognition. In particular, the DNN includes three feed-forward neural networks, which are trained according to a batch process utilizing a cohort set of negative training samples. After each batch of training samples is processed, the DNN may be trained according to a loss function, e.g., utilizing a cosine measure of similarity between respective samples, along with positive and negative margins, to provide a robust representation of voiceprints.

A processor-implemented method includes: extracting a target speaker voice feature based on an input voice of a target speaker; determining an utterance scenario of the input voice based on the target speaker voice feature; generating a final target speaker voice feature based on the determined utterance scenario; and determining whether the target speaker corresponds to a user based on the final target speaker voice feature and a final user voice feature, wherein the determined utterance scenario comprises either one of a single-speaker scenario and a multiple-speaker scenario.

Embodiments of systems and methods for intelligently selecting audio signatures based upon context information to perform management actions are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: select, based upon context information, a subset of a plurality of audio signatures, compare a received audio input to at least one audio signature among the subset of audio signatures to the exclusion of any other audio signature of the plurality of audio signatures, and, in response to the comparison indicating a match, perform one or more management actions.

An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.

An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.

An artificial intelligence-based control method is disclosed. In an artificial intelligence-based control method according to an exemplary embodiment of the present disclosure, when a user approaches within a set sensing range of a device, the device may capture a user image and predict whether the user has an intent to use the device by using motion features included in the captured image. An AI control method of the present disclosure may be associated with an artificial intelligent module, an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a 5G service-related device, etc.

An artificial intelligence-based control method is disclosed. In an artificial intelligence-based control method according to an exemplary embodiment of the present disclosure, when a user approaches within a set sensing range of a device, the device may capture a user image and predict whether the user has an intent to use the device by using motion features included in the captured image. An AI control method of the present disclosure may be associated with an artificial intelligent module, an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a 5G service-related device, etc.

A system described herein may provide a technique for the use of machine learning techniques to perform authentication, such as biometrics-based user authentication. For example, user biometric information (e.g., facial features, fingerprints, voice, etc.) of a user may be used to train a machine learning model, in addition to a noise vector. A representation of the biometric information (e.g., an image file including a picture of the user's face, an encoded file with vectors or other representation of the user's fingerprint, a sound file including the user's voice, etc.) may be iteratively transformed until the transformed biometric information matches the noise vector, and the machine learning model may be trained based on the set of transformations that ultimately yield the noise vector, when given the biometric information.