Patent
System for detecting voice activity
TLDR
In this paper, a nonlinear two-filter voice detection algorithm was proposed, in which one filter has a low time constant (the fast filter) and one filter had a high time constant(the slow filter).Abstract:
A system for detection of voice activity in a communications signal, employing a nonlinear two filter voice detection algorithm, in which one filter has a low time constant (the fast filter) and one filter has a high time constant (the slow filter). The slow filter serves to provide a noise floor estimate for the incoming signal, and the fast filter serves to more closely represent the total energy in the signal. The absolute value of incoming data is presented to both filters, and the difference in filter outputs is integrated over each of a series of successive frames, thereby giving an indication of the energy level above the noise floor in each frame of the incoming signal. Voice activity is detected if the measured energy level for a frame exceeds a specified threshold level. Silence (e.g., leaving only noise) is detected if the measured energy level for each of a specified number of successive frames does not exceed a specified threshold level. The system enables voice activity to be distinguished from common noise such as pops, clicks and low level cross-talk.read more
Citations
More filters
Patent
Instantaneous user initiation voice quality feedback
Muneyb Minhazuddin,Stephane Laveau,Alex M. Krumm-Heller,Neil Hepworth,Alexander Martin Scholte +4 more
TL;DR: A system for providing a high communications quality is provided in this paper, where the system comprises an input operable to receive a message from at least one of first and second network nodes 200 and 204, the message indicating a service problem with the session and a statistic collection agent 248 operable in response to the message, in order to cause reconfiguration of one or more attributes or resources in the network, variation of a sampling frequency of session-related performance attributes associated with the network; alteration of the types of session related performance attributes being collected regarding the network.
Patent
Voice modulation recognition in a radio-to-SIP adapter
Douglas Hall,Daniel Floyd +1 more
TL;DR: In this paper, a radio-to-SIP adapter is shown to include a voice detection algorithm processor as well as other circuitry to provide an interface between a radio and SIP adapter to accommodate a transition from half duplex to full duplex.
Patent
Voip endpoint call admission
TL;DR: In this paper, an intelligent endpoint or communication device that can collect available bandwidth-related information metrics and/or perform call admission control functions is presented, and the present invention is further directed to an architecture comprising a switch or media server in communication with a plurality of subscriber communication devices.
Patent
Packet prioritization and associated bandwidth and buffer management techniques for audio over IP
TL;DR: In this paper, an acoustic prioritization agent assigns a priority value to the packets based on factors such as whether the packet contains voice activity and the degree of acoustic similarity between this packet and adjacent packets in the sequence.
Patent
Time-sensitive-packet jitter and latency minimization on a shared data link
TL;DR: In this paper, a packet arrival prediction mechanism predicts when a time-critical packet is expected to arrive, and when transmission of a waiting lower-priority packet might cause a substantial delay in the expected timecritical packet's transmission, the lower priority packet is parked until it can be transmitted without interfering with a time critical packet.
References
More filters
Book
Digital Processing of Speech Signals
TL;DR: This paper presents a meta-modelling framework for digital Speech Processing for Man-Machine Communication by Voice that automates the very labor-intensive and therefore time-heavy and expensive process of encoding and decoding speech.
PatentDOI
Speech recognition system for an automotive vehicle
TL;DR: A speech recognition system includes speech presence detection which uses a first level threshold of ambient noise/silence above which speech start is decided for a signal as discussed by the authors, unless a predetermined time interval of speech is exceeded after start, causing a corrected second threshold to be calculated.
PatentDOI
Reduction of background noise for speech enhancement
Brant Martin Helf,Peter L. Chu +1 more
TL;DR: In this paper, human audio perception is used to perform spectral and time masking to reduce perceived loudness of noise added to speech signals, where a signal is divided into blocks and passed through notch filters to remove noise components and then appended to part of the previous block.
Patent
Method and apparatus for reducing residual far-end echo in voice communication networks
TL;DR: In this article, a method and apparatus for reducing the energy content that is attributable to echoes of signals transmitted into the local network (NEAR-IN signals) is described, in part, by generating a time-varying TEMPLATE signal which represents the smoothed energy content of NEARIN signals delayed according to the echo path and attenuated by an estimated echo transmission loss.
PatentDOI
Speech analysis/synthesis system with silence suppression
TL;DR: In this paper, a segment is classified as "speech" if the energy of the signal is greater than an adaptively adjusted threshold defined as the maximum of scaled values of two separate envelope parameters, which both track the variation in energy over the sequence of frames of speech data.