Adapting Automated Speech Recognition Parameters Based on Hotword Properties

A system comprising:

• data processing hardware;
• and
• memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
• receiving a first acoustic segment characterizing a hotword detected by a hotword detector in streaming audio captured by a user device;
• extracting one or more hotword attributes from the first acoustic segment wherein one of the one or more hotword attributes extracted from the first acoustic segment comprises a pause duration measure indicating an extent that a speaker paused while speaking the hotword and/or between speaking the hotword and a second acoustic segment that characterizes a spoken query/command that follows the first acoustic segment in the streaming audio captured by the user device;
• instructing an endpointer to one of increase or decrease an audio capture duration for the second acoustic segment from a default value based on the pause duration measure;
• adjusting, based on the one or more hotword attributes extracted from the first acoustic segment, one or more speech recognition parameters of an automated speech recognition (ASR) model;
• and
• after adjusting the speech recognition parameters of the ASR model and instructing the endpointer to one of increase or decrease the audio capture duration for the second acoustic segment, processing, using the ASR model, the second acoustic segment to generate a speech recognition result.