Digital radio signal receiver

A method for receiving a digital radio signal by a device, the method comprising:

• receiving an RF signal that includes a desired signal and interference;
• constructing a first signal and interference model during an off-device training stage;
• constructing a second signal and interference model during an on-device training stage based on the first signal and interference model and the RF signal received by the device;
• and
• decoding a set of data from the RF signal based on the second signal and interference model;
• wherein the off-device or on-device training stages represent the desired signal using a first trellis diagram and the interference using a second trellis diagram;
• and
• wherein the off-device or on-device training stages create the first and second signal and interference models by a Kronecker product matrix multiplication of the first trellis diagram with the second trellis diagram.

A digital radio signal receiver, comprising:

• an on-device training stage;
• and
• a decoder;
• wherein the receiver is configured to be coupled to a device;
• wherein the device is coupled to receive an RF signal;
• wherein the RF signal includes a desired signal and interference;
• wherein the receiver is configured to receive a first signal and interference model from an off-device training stage;
• wherein the on-device training stage is configured to construct a second signal and interference model based on the first signal and interference model and the RF signal received by the device;
• wherein the decoder is configured to generate a set of data from the RF signal based on the second signal and interference model;
• wherein the off-device or on-device training stages represent the desired signal using a first trellis diagram and the interference using a second trellis diagram;
• and
• wherein the off-device training stage is configured to parameterize the first signal and interference model by interpreting the first and second trellis representations as a combination of Hidden Markov Models (HMM) and a shallow neural network (NN).