InterSpeech 2021

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
(3 minutes introduction)

Swayambhu Nath Ray (Amazon, India), Minhua Wu (Amazon, USA), Anirudh Raju (Amazon, USA), Pegah Ghahremani (Amazon, USA), Raghavendra Bilgi (Amazon, India), Milind Rao (Amazon, USA), Harish Arsikere (Amazon, India), Ariya Rastrow (Amazon, USA), Andreas Stolcke (Amazon, USA), Jasha Droppo (Amazon, USA)
Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional information to improve a recurrent neural network-transducer (RNN-T) based automatic speech recognition (ASR) system. An audio-to-intent (A2I) model encodes the intent of the utterance in the form of embeddings or posteriors, and these are used as auxiliary inputs for RNN-T training and inference. Experimenting with a 50k-hour far-field English speech corpus, this study shows that when running the system in non-streaming mode, where intent representation is extracted from the entire utterance and then used to bias streaming RNN-T search from the start, it provides a 5.56% relative word error rate reduction (WERR). On the other hand, a streaming system using per-frame intent posteriors as extra inputs for the RNN-T ASR system yields a 3.33% relative WERR. A further detailed analysis of the streaming system indicates that our proposed method brings especially good gain on media-playing related intents (e.g. 9.12% relative WERR on PlayMusicIntent).