paper-with-me

홈 › Papers

Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over

2024-06-27 · Atsunori Ogawa, Naoyuki Kamo, Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Takatomo Kano, Naohiro Tawara, Marc Delcroix

Large language models (LLMs) have been successfully applied for rescoring automatic speech recognition (ASR) hypotheses. However, their ability to rescore ASR hypotheses of casual conversations has not been sufficiently explored. In this study, we reveal it by performing N-best ASR hypotheses rescoring using Llama2 on the CHiME-7 distant ASR (DASR) task. Llama2 is one of the most representative LLMs, and the CHiME-7 DASR task provides datasets of casual conversations between multiple participants. We investigate the effects of domain adaptation of the LLM and context carry-over when performing N-best rescoring. Experimental results show that, even without domain adaptation, Llama2 outperforms a standard-size domain-adapted Transformer-LM, especially when using a long context. Domain adaptation shortens the context length needed with Llama2 to achieve its best performance, i.e., it reduces the computational cost of Llama2.

📄 PDF Abstract BibTeX arXiv:2406.18972

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain Adaptationspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

ProGRes: Prompted Generative Rescoring on ASR n-Best

2024-08-30 · Ada Defne Tur, Adel Moumen, Mirco Ravanelli

Large Language Models (LLMs) have shown their ability to improve the performance of speech recognizers by effectively rescoring the n-best hypotheses generated during the beam search process. However, the best way to exp…

speech-recognitionSpeech Recognition

Lattention: Lattice-attention in ASR rescoring

2021-11-19 · Prabhat Pandey, Sergio Duarte Torres, Ali Orkan Bayer, Ankur Gandhe 외

Lattices form a compact representation of multiple hypotheses generated from an automatic speech recognition system and have been shown to improve performance of downstream tasks like spoken language understanding and sp…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognition+3

DNN-Based Semantic Model for Rescoring N-best Speech Recognition List

2020-11-02 · Dominique Fohr, Irina Illina

The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models

2023-12-20 · Atsunori Ogawa, Naohiro Tawara, Marc Delcroix, Shoko Araki

We investigate the effectiveness of using a large ensemble of advanced neural language models (NLMs) for lattice rescoring on automatic speech recognition (ASR) hypotheses. Previous studies have reported the effectivenes…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition

2025-01-16 · Takaaki Hori, Martin Kocour, Adnan Haider, Erik McDermott 외

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language mode…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition