Patent
Voice Recognition Accuracy in High Noise Conditions
Reads0
Chats0
TLDR
In this paper, the authors used adaptive thresholds to determine the presence of speech and to generate noise-dependent triggers for indicating the presence or absence of speech during high-noise conditions.Abstract:
Systems and methods for voice recognition determine energy levels for speech and noise and generate adaptive thresholds based on the determined energy levels. The adaptive thresholds are applied to determine the presence of speech and to generate noise-dependent triggers for indicating the presence of speech during high-noise conditions. In an embodiment, the signal energy is averaged in the presence of speech and in the presence of background noise. Audio energy calculations may be made by averaging via a sliding window or via a memory filter.read more
Citations
More filters
Patent
Mobile terminal and method for controlling the same
TL;DR: In this article, a mobile terminal including a body; a touchscreen provided to a front and extending to side of the body and configured to display content; and a controller configured to detect one side of a body when it comes into contact with a side of an external terminal, display a first area on the touchscreen corresponding to a contact area of body and the external terminal and a second area including the content.
Patent
Detection of liveness
TL;DR: In this article, the authors proposed a method for detecting the liveness of a speaker based on the reflection of the ultrasound signal and the level of the reflected ultrasound and the monitored ambient ultrasound noise.
Patent
Detection of replay attack
TL;DR: In this paper, a neural network is trained to distinguish autocorrelations formed from speech signals resulting from replay attacks from autocors formed from the speech signals not resulting from the replay attacks.
Patent
Apparatus, system and method for directing voice input in a controlling device
TL;DR: In this paper, a system and method for controlling a controllable appliance resident in an environment which includes a device adapted to receive speech input is presented, where the system establishes a noise threshold for the environment in which the device is operating, receives at the device a speech input, determines a noise level for the environments at the time the input is received by the device, compares the determined noise level to the established noise threshold, and causes one or more commands to be automatically issued to the device to transition from a first volume level to a second volume level that is less than the
Patent
Voice input processing method and electronic device for supporting the same
TL;DR: In this article, an electronic device includes a microphone, a communication circuitry, an indicator configured to provide at least one visual indication, and a processor configured to be electrically connected with the microphone, the communication circuitry and the indicator.
References
More filters
Patent
Systems and methods for audio signal processing
TL;DR: In this article, a method for signal level matching by an electronic device is described, which includes capturing a plurality of audio signals from multiple microphones and determining a difference signal based on an inter-microphone subtraction.
Patent
Method for the detection of speech segments
TL;DR: In this article, a method for the detection of noise and speech segments in a digital audio input signal is proposed, in which the input signal being divided into a plurality of frames comprising: - a first stage (10), in which a first classification of a frame as noise is performed if the mean energy value for this frame and the previous N frames is not greater than a first energy threshold, N>1; - a second stage (20) in which for each frame that has not been classified as noise in the first stage, it is decided if said frame is classified as
Patent
Speech processing device, speech processing method, and speech processing program
TL;DR: In this paper, a speech processing device includes a reverberation characteristic selection unit configured to correlate correction data indicating a contribution of reverberation component based on a corresponding reverberation characteristics with an adaptive acoustic model which is trained using reverbed speech, to calculate likelihoods based on the adaptive acoustic models for a recorded speech, and to select correction data corresponding to the model having the calculated highest likelihood.
Patent
Partially filling mixed-initiative forms from utterances having sub-threshold confidence scores based upon word-level confidence data
TL;DR: In this article, a single spoken utterance including content for multiple elements can be received, where each element is mapped to a data field and utterance level confidence score can be determined, which can fall below an associated certainty threshold.
PatentDOI
Method of detecting the presence of speech in a telephone signal and speech detector implementing said method
Dominique Lajotte,Francis Menet +1 more
TL;DR: In a method of detecting the presence of speech in a telephone signal, a signal sequence is interpreted as constituting speech if its mean power level exceeds a threshold, the value of which is decreased as the number of passages through zero level in the sequence approaches 1.25 per millisecond.