Speech processing method and apparatus, and electronic device

A speech processing apparatus, comprising:

• at least one processor, and
• at least one memory communicatively coupled to the at least one processor and storing instructions that upon execution by the at least one processor cause the apparatus to:
• receive a speech block to be identified as a current speech block, wherein the speech block comprises a past frame, a current frame and a future frame;
• and
• to perform a speech identification process based on the current speech block, wherein the speech identification process comprises:
• performing speech identification based on the current speech block to obtain a speech identification result of the current frame and a speech identification result of the future frame;
• determining whether a previous speech block for the current speech block exists, wherein a current frame of the previous speech block is before and adjacent to the current frame of the current speech block;
• in a case that the previous speech block for the current speech block exists, updating a target identification result based on the speech identification result of the current frame of the current speech block, wherein the target identification result comprises a speech identification result of a future frame of the previous speech block;
• and
• outputting the speech identification result of the future frame of the current speech block.

A computer-readable non-transitory medium,

• bearing computer-readable instructions that upon execution on a computing device cause the computing device at least to:
• receive a speech block to be identified as a current speech block, wherein the speech block comprises a past frame, a current frame and a future frame;
• perform a speech identification process based on the current speech block, wherein the speech identification process comprises:
• performing speech identification based on the current speech block to obtain a speech identification result of the current frame and a speech identification result of the future frame;
• determining whether a previous speech block for the current speech block exists, wherein a current frame of the previous speech block is before and adjacent to the current frame of the current speech block;
• in a case that the previous speech block for the current speech block exists, updating a target identification result based on the speech identification result of the current frame of the current speech block, wherein the target identification result comprises a speech identification result of a future frame of the previous speech block;
• and
• outputting the speech identification result of the future frame of the current speech block.