An efficient text augmentation approach for contextualized Mandarin speech recognition

Autor:	Zheng, Naijun, Wan, Xucheng, Liu, Kai, Du, Ziqing, Huan, Zhou
Rok vydání:	2024
Předmět:	Computer Science - Sound Computer Science - Computation and Language Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: accepted to interspeech2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.09950 Zobrazit plný text záznamu View this record from Arxiv