Automated transcript generation from multi-channel audio

A non-transitory computer-readable medium having stored thereon executable instructions that direct a computer system to perform operations comprising:

• receiving speaker identification information for each of a plurality of audio channels, wherein the speaker identification information for each individual audio channel identifies a person assigned to the individual audio channel, wherein each of the plurality of audio channels are associated with a different microphone of a plurality of microphones;
• receiving multi-channel streaming audio on the plurality of audio channels, wherein the multi-channel streaming audio comprises audio signals captured from each of the plurality of microphones on a different channel of the plurality of audio channels;
• applying one or more filters to each channel of the multi-channel streaming audio to generate a plurality of filtered audio channels, such that each of the filtered audio channels includes speech utterances spoken by a different person assigned to the individual corresponding audio channel;
• applying automatic speech recognition to audio from each of the filtered audio channels to obtain text results for each of the filtered audio channels, wherein the text results for each of the filtered audio channels represent words spoken by a different speaker;
• and
• generating a transcript of at least a portion of multi-speaker conversation based on the text results, wherein the transcript includes text assembled from text results of at least two different filtered audio channels in an order based on timestamp information, and wherein the transcript identifies the speaker of each word in the portion of the multi-speaker conversation based on speaker identification information received for a respective audio channel from which the word was identified.

A system comprising:

• a plurality of microphones;
• audio mixer hardware configured to process a plurality of audio channels, wherein each of the plurality of microphones corresponds to a different channel of the plurality of audio channels;
• and
• a computing system in communication with the audio mixer hardware and comprising memory and a processor, the computing system configured with processor-executable instructions to perform operations comprising:
• receiving speaker identification information for each of the plurality of audio channels, wherein the speaker identification information for each individual audio channel identifies a person assigned to the individual audio channel, wherein each of the plurality of audio channels are associated with a different microphone of the plurality of microphones;
• receiving at least a portion of multi-channel streaming audio from the audio mixer hardware, wherein the multi-channel streaming audio comprises audio signals captured from each of the plurality of microphones on a different channel of the plurality of audio channels;
• applying one or more filters to each channel of the multi-channel streaming audio to generate a plurality of filtered audio channels, such that each of the filtered audio channels includes speech utterances spoken by a different person assigned to the individual corresponding audio channel;
• applying automatic speech recognition to audio from each of the filtered audio channels to obtain text results for each of the filtered audio channels, wherein the text results for each of the filtered audio channels represent words spoken by a different speaker;
• and
• generating a real-time transcript of at least a portion of multi-speaker conversation based on the text results, wherein the real-time transcript is generated while the multi-channel streaming audio continues to be received from the audio mixer hardware, wherein the real-time transcript includes text assembled from text results of at least two different filtered audio channels in an order based on timestamp information, and wherein the transcript identifies the speaker of each word in the portion of the multi-speaker conversation based on speaker identification information received for a respective audio channel from which the word was identified.