LongFNT: Long-form Speech Recognition with Factorized Neural Transducer
원문 초록
Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows no much gain in our preliminary experiments, since the prediction network is not a pure language model. This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor. We propose the {LongFNT-Text} architecture, which fuses the sentence-level long-form features directly with the output of the vocabulary predictor and then embeds token-level long-form features inside the vocabulary predictor, with a pre-trained contextual encoder RoBERTa to further boost the performance. Moreover, we propose the {LongFNT} architecture by extending the long-form speech to the original speech input and achieve the best performance. The effectiveness of our LongFNT approach is validated on LibriSpeech and GigaSpeech corpora with 19% and 12% relative word error rate~(WER) reduction, respectively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models
Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
Improving Named Entity Transcription with Contextual LLM-based Revision
Automatic Speech Recognition of African American English: Lexical and Contextual Effects
Customizing Speech Recognition Model with Large Language Model Feedback
토론
이 논문과 연결된 포럼 글이 아직 없습니다.