Attention-based Contextual Language Model Adaptation for Speech Recognition
share
Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance was spoken, provides a rich input signal. We introduce an attention mechanism for training neural speech recognition language models on both text and non-linguistic contextual data. When applied to a large de-identified dataset of utterances collected by a popular voice assistant platform, our method reduces perplexity by 7.0 that does not incorporate contextual information. When evaluated on utterances extracted from the long tail of the dataset, our method improves perplexity by 9.0 state-of-the-art model for contextual LM.
READ FULL TEXT
