Modular Hybrid Autoregressive Transducer
원문 초록
Text-only adaptation of a transducer model remains challenging for end-to-end speech recognition since the transducer has no clearly separated acoustic model (AM), language model (LM) or blank model. In this work, we propose a modular hybrid autoregressive transducer (MHAT) that has structurally separated label and blank decoders to predict label and blank distributions, respectively, along with a shared acoustic encoder. The encoder and label decoder outputs are directly projected to AM and internal LM scores and then added to compute label posteriors. We train MHAT with an internal LM loss and a HAT loss to ensure that its internal LM becomes a standalone neural LM that can be effectively adapted to text. Moreover, text adaptation of MHAT fosters a much better LM fusion than internal LM subtraction-based methods. On Google's large-scale production data, a multi-domain MHAT adapted with 100B sentences achieves relative WER reductions of up to 12.4% without LM fusion and 21.5% with LM fusion from 400K-hour trained HAT.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models
NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025
Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
토론
이 논문과 연결된 포럼 글이 아직 없습니다.