A Deliberation-based Joint Acoustic and Text Decoder
원문 초록
We propose a new two-pass E2E speech recognition model that improves ASR performance by training on a combination of paired data and unpaired text data. Previously, the joint acoustic and text decoder (JATD) has shown promising results through the use of text data during model training and the recently introduced deliberation architecture has reduced recognition errors by leveraging first-pass decoding results. Our method, dubbed Deliberation-JATD, combines the spelling correcting abilities of deliberation with JATD's use of unpaired text data to further improve performance. The proposed model produces substantial gains across multiple test sets, especially those focused on rare words, where it reduces word error rate (WER) by between 12% and 22.5% relative. This is done without increasing model size or requiring multi-stage training, making Deliberation-JATD an efficient candidate for on-device applications.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
OpusLM: A Family of Open Unified Speech Language Models
Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition
Whale: Large-Scale multilingual ASR model with w2v-BERT and E-Branchformer with large speech data
HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation
MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.