A rule-based end-pointer isolates spoken utterances contained within an audio stream from background noise and non-speech transients. The rule-based end-pointer includes a plurality of rules to determine the beginning and/or end of a spoken utterance based on various speech characteristics. The rules may analyze an audio stream or a portion of an audio stream based upon an event, a combination of events, the duration of an event, or a duration relative to an event. The rules may be manually or dynamically customized depending upon factors that may include characteristics of the audio stream itself, an expected response contained within the audio stream, or environmental conditions.

Speech end-pointer

Systems and methods for multi-sourced noise suppression are provided. An example system may receive streams of audio data including a voice signal and noise, the voice signal including a spoken word. The streams of audio data are provided by distributed audio devices. The system can assign weights to the audio streams based at least partially on quality of the audio streams. The weights of audio streams can be determined based on signal-to-noise ratios (SNRs). The system may further process, based on the weights, the audio stream to generate cleaned speech. Each audio device comprises microphone(s) and can be associated with the Internet of Things (IoT), such that the audio devices are Internet of Things devices. The processing can include noise suppression and reduction and echo cancellation. The cleaned speech can be provided to a remote device for further processing which may include Automatic Speech Recognition (ASR).

Multi-Sourced Noise Suppression

Wind and other noise is suppressed in a signal by adaptively changing characteristics of a filter. The filter characteristics are changed in response to the noise content of the signal over time using a history of noise content. Filter characteristics are changed according to a plurality of reference filters, the characteristics of which are chosen to optimally attenuate or amplify signals in a range of frequencies.

Method and apparatus for masking wind noise

Described are noise suppression techniques applicable to various systems including automatic speech processing systems in digital audio pre-processing. The noise suppression techniques utilize a machine-learning framework trained on cues pertaining to reference clean and noisy speech signals, and a corresponding synthetic noisy speech signal combining the clean and noisy speech signals. The machine-learning technique is further used to process audio signals in real time by extracting and analyzing cues pertaining to noisy speech to dynamically generate an appropriate gain mask, which may eliminate the noise components from the input audio signal. The audio signal pre-processed in such a manner may be applied to an automatic speech processing engine for corresponding interpretation or processing. The machine-learning technique may enable extraction of cues associated with clean automatic speech processing features, which may be used by the automatic speech processing engine for various automatic speech processing.

Noise suppression for speech processing based on machine-learning mask estimation

Embodiments of the present invention relate to a voice detector receiving an input signal that is divided into sub-signals that represent a frequency sub-band. The voice detector calculates, for each sub-band, a signal-to-noise (SNR) value based on a corresponding sub-signal for each sub-band and a background signal for each sub-band. The voice detector also calculates a power SNR value for each sub-band, where at least one of the power SNR values is calculated based on a non-linear function. The voice detector forms a single value based on the calculated power SNR values and compares the single value and a given threshold value to make a voice activity decision presented on an output port.

Voice detector and a method for suppressing sub-bands in a voice detector

The present invention relates to a method and apparatus for detecting voice activity in a communication signal, wherein filter means are provided for estimating or suppressing an offset component of the level of the communication signal. A filter parameter is controlled based on the output of the filter means. Furthermore, the estimation or suppression of the offset component is limited in response to the output of the filter means. The filter means may be based on a non-linear adaptive notch level filter or a noise floor tracking filter. Thereby, the tracking behavior of noise floor estimation to sudden rises in noise floor can be improved and the voice activity detection can work efficiently over a wide dynamic range.

Wolfgang Brox

Papers

Voice activity detection with adaptive noise floor tracking