View publication

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in inferring user-intent. We first present a transformer-based approach for punctuation prediction that achieves 8% improvement on the IWSLT 2012 TED Task, beating the previous state of the art [1]. We next describe our multimodal model that learns from both text and audio, which achieves 8% improvement over the text-only algorithm on an internal dataset for which we have both the audio and transcriptions. Finally, we present an approach to learning a model using contextual dropout that allows us to handle variable amounts of future context at test time.

Related readings and updates.

Apple at ICASSP 2021

Apple is sponsoring the 46th International Conference on Acoustics, Speech, and Signal Processing (ICASSP). The conference focuses on signal processing and its applications and takes place virtually from June 6 to 11.

See event details

Knowledge Transfer for Efficient On-device False Trigger Mitigation

Pranay Dighe, Erik Marchi, Srikanth Vishnubhotla, Sachin Kajarekar, Devang Naik

See paper details