2 papers
eess.AS2022
Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments
Joe Caroselli, Arun Narayanan, Yiteng Huang
One of the most challenging scenarios for smart speakers is multi-talker, when target speech from the desired speaker is mixed with interfering speech from one or more speakers. A…
eess.AS2022
Cleanformer: A multichannel array configuration-invariant neural enhancement frontend for ASR in smart speakers
Joseph Caroselli, Arun Narayanan, Nathan Howard +1
This work introduces the Cleanformer, a streaming multichannel neural based enhancement frontend for automatic speech recognition (ASR). This model has a conformer-based architectu…