paper-with-me

Papers

Retrieval-Augmented Speech Recognition Approach for Domain Challenges

2025-02-21 · Peng Shen, Xugang Lu, Hisashi Kawai

Speech recognition systems often face challenges due to domain mismatch, particularly in real-world applications where domain-specific data is unavailable because of data accessibility and confidentiality constraints. Inspired by Retrieval-Augmented Generation (RAG) techniques for large language models (LLMs), this paper introduces a LLM-based retrieval-augmented speech recognition method that incorporates domain-specific textual data at the inference stage to enhance recognition performance. Rather than relying on domain-specific textual data during the training phase, our model is trained to learn how to utilize textual information provided in prompts for LLM decoder to improve speech recognition performance. Benefiting from the advantages of the RAG retrieval mechanism, our approach efficiently accesses locally available domain-specific documents, ensuring a convenient and effective process for solving domain mismatch problems. Experiments conducted on the CSJ database demonstrate that the proposed method significantly improves speech recognition accuracy and achieves state-of-the-art results on the CSJ dataset, even without relying on the full training data.

📄 PDF Abstract BibTeX arXiv:2502.15264

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderRAGRetrievalRetrieval-augmented Generationspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Weight Decay 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
WordPiece 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

RASST: Retrieval-Augmented Simultaneous Speech Translation

2026-01-30 · Jiaxuan Luo, Siqi Ouyang, Jiaxing Xu, Lei Li arxiv

Simultaneous speech translation produces target text incrementally from partial speech input. Recent speech large language models have markedly improved SST quality but still struggle with rare and domain-specific termin…

Cross-Modal RetrievalMachine TranslationSpeech Recognition

RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition

2025-08-05 · Pengcheng Wang, Sheng Li, Takahiro Shinozaki arxiv

In this paper, we propose RAG-Boost (ST-ShinozakiLab Task I system), which enhances the baseline LLM-based ASR system of the MLC-SLM Challenge (task I) with a retrieval-augmented generation (RAG) module on the fly. Each …

Speech Recognition

Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunities

2023-04-25 · Christophe Van Gysel

Virtual assistants are becoming increasingly important speech-driven Information Retrieval platforms that assist users with various tasks. We discuss open problems and challenges with respect to modeling spoken informati…

domain classificationInformation RetrievalKnowledge GraphsRetrieval+2

SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation

2025-01-26 · ChunYu Sun, Bingyu Liu, Zhichao Cui, Anbin QI 외

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+6

Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction

2026-06-19 · Mohammad Aref Jafari-Raddani arxiv

End-to-end automatic speech recognition systems frequently hallucinate rare entities and domain-specific terms, especially in low-resource languages. While retrieval-augmented generation frameworks can mitigate these err…

Speech Recognition