Adaptive interface in a voice-based networked system

A system to generate voice-based interfaces in a networked system, comprising at least one server device comprising a memory and one or more processors to:

• receive, by an automated assistant executed by the one or more processors of the at least one server device, audio data detected at a client device that includes an automated assistant interface for interacting with the automated assistant;
• parse, by a speech recognition engine executed by the one or more processors, with one or more acoustic models the audio data to detect an invocation phrase configured to invoke the automated assistant;
• determine, by the speech recognition engine, that first portion of the audio data including the invocation phrase corresponds to a user profile that is accessible to the automated assistant;
• select, by the speech recognition engine, a language and a speech recognition model assigned to the user profile;
• parse, by the speech recognition engine, a second portion of audio data with the speech recognition model to identify a request and a keyword;
• select, by a content selector component executed by the one or more processors, a first digital component based on the request identified in the second portion of the audio data and a second digital component based on the keyword identified in the second portion of the audio data and the language;
• and
• transmit, by the content selector component, the first digital component and the second digital component to the client device for presentation in response to the audio data.

A method to generate voice-based interfaces in a networked system, the method comprising:

• receiving, by an automated assistant executed by one or more processors of at least one server device, audio data detected at a client device that includes an automated assistant interface for interacting with the automated assistant;
• parsing, by a speech recognition engine executed by the one or more processors, with one or more acoustic models the audio data to detect an invocation phrase configured to invoke the automated assistant;
• determining, by the speech recognition engine, that first portion of the audio data including the invocation phrase corresponds to a user profile that is accessible to the automated assistant;
• selecting, by the speech recognition engine, a language and a speech recognition model assigned to the user profile;
• parsing, by the speech recognition engine, a second portion of audio data with the speech recognition model to identify a request and a keyword;
• selecting, by a content selector component executed by the one or more processors, a first digital component based on the request identified in the second portion of the audio data and a second digital component based on the keyword identified in the second portion of the audio data and the language;
• and
• transmitting, by the content selector component, the first digital component and the second digital component to the client device for presentation in response to the audio data.