Amazon Transcribe Medical now supports both streaming and batch transcription of multi-channel audio
Amazon Transcribe Medical is a HIPAA-eligible automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capabilities to their healthcare and life science applications. Starting today, you can use the new Channel Identification feature to transcribe the speech from both live audio streams or static audio files that contain multiple audio channels. With Channel Identification, you can process audio from multiple channel to generate a single transcript of the conversation complete with channel labels.
Channel Identification is a powerful feature that can enable medical transcription for a variety of use cases. In drug-safety monitoring, contact centers of pharmaceutical companies often analyze phone calls, which consists two audio channels (e.g. caller versus agent). Using Channel Identification allows a call-analytics solution to disaggregate the speech for each channel, transcribe them separately, and then produce a consolidated transcript for analysis. Similarly in telehealth, a clinician and a patient often dial into the same virtual meeting using separate devices (e.g. separate audio channels). Telehealth solution providers can now use Channel Identification to independently transcribe the patient and clinician audio channels and provide real-time conversational subtitles.
Channel Identification for Amazon Transcribe Medical is available in all AWS Regions where the service operates at no additional cost. Give the feature a try by visiting our service console today! For more information, visit Transcribing Multi-Channel Audio.