In speech recognition applications, it is important to recognize context-specific rare words, such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise for this purpose, which efficiently biases such words with a prefix tree. While the original TCPGen relies on grapheme-based encoding, we propose extending it with phoneme-aware encoding to better recognize words of unusual pronunciations. As TCPGen handles biasing words as subword units, we propose obtaining subword-level phoneme-aware encoding by using alignment between phonemes and subwords. Furthermore, we propose injecting phoneme-level predictions from CTC into queries of TCPGen so that the model better interprets the phoneme-aware encodings. We conducted ASR experiments with TCPGen for RNN transducer. We observed that proposed phoneme-aware encoding outperformed ordinary grapheme-based encoding on both the English LibriSpeech and Japanese CSJ datasets, demonstrating the robustness of our approach across linguistically diverse languages.

翻译：在语音识别应用中，识别上下文特定的稀有词汇（如专有名词）具有重要意义。树约束指针生成器（TCPGen）通过前缀树高效地偏置此类词汇，展现出良好前景。原始TCPGen依赖基于字素的编码，我们提出扩展音素感知编码以更好识别发音异常词汇。由于TCPGen将偏置词看作子词单元，我们提出利用音素与子词的对齐关系获取子词级音素感知编码。此外，我们建议将CTC的音素级预测注入TCPGen的查询中，使模型能更准确解读音素感知编码。我们在RNN换能器上进行了TCPGen的语音识别实验。实验表明，所提出的音素感知编码在英语LibriSpeech和日语CSJ数据集上均优于传统基于字素的编码，证明了该方法在语言多样性上的鲁棒性。