Method and system for signal transmission control

A method, comprising:

• receiving or accessing an audio signal that comprises a plurality of temporally sequential blocks or frames;
• determining two or more features that characterize aggregately two or more of the sequential audio blocks or frames that have been processed previously within a time period that is recent in relation to a current point in time, wherein the feature determination exceeds a specificity criterion and is delayed in relation to the recently processed audio blocks or frames;
• detecting an indication of voice activity in the audio signal, wherein the voice activity detection (VAD) is based on a decision that exceeds a preset sensitivity threshold and that is computed over a time period, which is brief in relation to the duration of each of the audio signal blocks or frames, and wherein the decision relates to one or more features of a current audio signal block or frame;
• combining the high sensitivity short term VAD, the recent high specificity audio block or frame feature determination and information that relates to a state, which is based on a history of one or more previously computed feature determinations that are compiled from a plurality of features that are determined over a time that is prior to the recent high specificity audio block or frame feature determination time period;
• and
• outputting a decision relating to a commencement or termination of the audio signal, or a gain related thereto, based on the combination, wherein
• said state information includes a nuisance level associated with the audio signal, the nuisance level indicating a possibility that a nuisance state exists at the present frame, wherein
• the nuisance level is increased with a first rate if the present frame is the last frame of a present voice segment and a voice ratio of the immediately previous frame is less than a nuisance threshold, the voice ratio representing a prediction made at the time of the present frame, about a possibility that the next frame includes voice, and
• the nuisance level is decreased with a second rate, the second rate faster than the first rate, if
• the present frame is within the present voice segment,
• the voice ratio of the present frame is greater than a voice ratio threshold value,
• and the portion of the present voice segment from its start to the present frame is longer than a time period threshold value.

An apparatus, comprising:

• an inputting unit configured to receive or access an audio signal that comprises a plurality of temporally sequential blocks or frames;
• a feature generator configured to determine two or more features that characterize aggregately two or more of the sequential audio blocks or frames that have been processed previously within a time period that is recent in relation to a current point in time, wherein the feature determination exceeds a specificity criterion and is delayed in relation to the recently processed audio blocks or frames;
• a detector configured to detect an indication of voice activity in the audio signal, wherein the voice activity detection (VAD) is based on a decision that exceeds a preset sensitivity threshold and that is computed over a time period, which is brief in relation to the duration of each of the audio signal blocks or frames, and wherein the decision relates to one or more features of a current audio signal block or frame;
• a combining unit configured to combine the high sensitivity short term VAD, the recent high specificity audio block or frame feature determination and information that relates to a state, which is based on a history of one or more previously computed feature determinations that are compiled from a plurality of features that are determined over a time that is prior to the recent high specificity audio block or frame feature determination time period;
• and
• a decision maker configured to output a decision relating to a commencement or termination of the audio signal, or a gain related thereto, based on the combination, wherein said state information includes a nuisance level associated with the audio signal, the nuisance level indicating a possibility that a nuisance state exists at the present frame, wherein
• the nuisance level is increased with a first rate if the present frame is the last frame of a present voice segment and a voice ratio of the immediately previous frame is less than a nuisance threshold, the voice ratio representing a prediction made at the time of the present frame, about a possibility that the next frame includes voice, and
• the nuisance level is decreased with a second rate, the second rate faster than the first rate, if
• the present frame is within the present voice segment,
• the voice ratio of the present frame is greater than a voice ratio threshold value,
• and the portion of the present voice segment from its start to the present frame is longer than a time period threshold value.