An efficient text augmentation approach for contextualized Mandarin speech recognition
This addresses data scarcity in contextualized ASR for Mandarin, offering a computationally efficient solution, though it is incremental as it builds on existing pre-trained models and codebook methods.
The paper tackles the problem of limited speech-text data for contextualized Mandarin ASR by proposing a text-augmentation technique that uses text-only data to enhance pre-trained models, resulting in up to 30% relative CER improvement on rare words and 15% across all words.
Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this challenge, our study proposes to leverage extensive text-only datasets and contextualize pre-trained ASR models using a straightforward text-augmentation (TA) technique, all while keeping computational costs minimal. In particular, to contextualize a pre-trained CIF-based ASR, we construct a codebook using limited speech-text data. By utilizing a simple codebook lookup process, we convert available text-only data into latent text embeddings. These embeddings then enhance the inputs for the contextualized ASR. Our experiments on diverse Mandarin test sets demonstrate that our TA approach significantly boosts recognition performance. The top-performing system shows relative CER improvements of up to 30% on rare words and 15% across all words in general.