Abstract: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

Abstract: A Learning Enhanced Simulated Annealing (LESA) method is provided. Based on a Simulated Annealing (SA) framework, this method adds a Knowledge Base (KB) initialized at the beginning of the search and updated at each iteration, which memorizes a portion of the search history and guides the further search through a KB trial generator. The basic idea of LESA is that its search history is stored in a KB, and a KB trial generator extracts information from it and uses it to generate a new trial. The next move of the search is the weighted sum of the trial generated by the KB trial generator and the trial generated by the usual SA trial generator. The knowledge base is then updated after each search iteration.

Abstract: A gain-constrained noise suppression for speech more precisely estimates noise, including during speech, to reduce musical noise artifacts introduced from noise suppression. The noise suppression operates by applying a spectral gain G(m, k) to each short-time spectrum value S(m, k) of a speech signal, where m is the frame number and k is the spectrum index. The spectrum values are grouped into frequency bins, and a noise characteristic estimated for each bin classified as a “noise bin.” An energy parameter is smoothed in both the time domain and the frequency domain to improve noise estimation per bin. The gain factors G(m, k) are calculated based on the current signal spectrum and the noise estimation, then smoothed before being applied to the signal spectral values S(m, k).

Abstract: A Learning Enhanced Simulated Annealing (LESA) method is provided. Based on a Simulated Annealing (SA) framework, this method adds a Knowledge Base (KB) initialized at the beginning of the search and updated at each iteration, which memorizes a portion of the search history and guides the further search through a KB trial generator. The basic idea of LESA is that its search history is stored in a KB, and a KB trial generator extracts information from it and uses it to generate a new trial. The next move of the search is the weighted sum of the trial generated by the KB trial generator and the trial generated by the usual SA trial generator. The knowledge base is then updated after each search iteration.

Abstract: A gain-constrained noise suppression for speech more precisely estimates noise, including during speech, to reduce musical noise artifacts introduced from noise suppression. The noise suppression operates by applying a spectral gain G(m, k) to each short-time spectrum value S(m, k) of a speech signal, where m is the frame number and k is the spectrum index. The spectrum values are grouped into frequency bins, and a noise characteristic estimated for each bin classified as a “noise bin.” An energy parameter is smoothed in both the time domain and the frequency domain to improve noise estimation per bin. The gain factors G(m, k) are calculated based on the current signal spectrum and the noise estimation, then smoothed before being applied to the signal spectral values S(m, k).