Abstract: Disclosed are a speech interaction method, computer readable storage medium, and electronic device, improving processing efficiency in multi-channel speech interaction scenarios with low resource consumption and processing delay. The method includes: obtaining at least one channel of audio signal; recognizing the at least one channel of audio signal using a preset speech recognition model, to obtain a first type of recognition result; determining stored recognition data from a buffer; generating a second type of recognition result based on the stored recognition data; processing the first and second type of results using the model, to obtain at least one statement recognition result corresponding to the at least one channel of audio signal; performing semantic parsing on the statement recognition result, to obtain at least one parsing result; and generating, based on the at least one parsing result, an instruction for controlling a speech interaction device to perform a corresponding function.

Abstract: The present disclosure provides a speech recognition method and device. The method includes: receiving a speech signal; decoding the speech signal according to an acoustic model, a language model and a decoding network established in advance, and dynamically adding a blank unit in a decoding process to obtain an optimum decoding path with the added blank unit, in which the acoustic model is obtained based on connectionist temporal classification training, the acoustic model includes basic pronunciation units and the blank unit, and the decoding network includes a plurality of decoding paths consisting of the basic pronunciation units; and outputting the optimum decoding path as a recognition result of the speech signal.

Abstract: The present disclosure provides a speech recognition method and device. The method includes: receiving a speech signal; decoding the speech signal according to an acoustic model, a language model and a decoding network established in advance, and dynamically adding a blank unit in a decoding process to obtain an optimum decoding path with the added blank unit, in which the acoustic model is obtained based on connectionist temporal classification training, the acoustic model includes basic pronunciation units and the blank unit, and the decoding network includes a plurality of decoding paths consisting of the basic pronunciation units; and outputting the optimum decoding path as a recognition result of the speech signal.