paper-with-me

홈 › Papers

On Language Model Integration for RNN Transducer based Speech Recognition

2021-10-13 · Wei Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to remove this sequence prior as ILM correction. In this work, we study various ILM correction-based LM integration methods formulated in a common RNN-T framework. We provide a decoding interpretation on two major reasons for performance improvement with ILM correction, which is further experimentally verified with detailed analysis. We also propose an exact-ILM training framework by extending the proof given in the hybrid autoregressive transducer, which enables a theoretical justification for other ILM approaches. Systematic comparison is conducted for both in-domain and cross-domain evaluation on the Librispeech and TED-LIUM Release 2 corpora, respectively. Our proposed exact-ILM training can further improve the best ILM method.

📄 PDF Abstract BibTeX arXiv:2110.06841

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition

2024-12-21 · Keqi Deng, Jinxi Guo, Yingyi Ma, Niko Moritz 외

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, t…

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

An Empirical Study of Language Model Integration for Transducer based Speech Recognition

2022-03-31 · Huahuan Zheng, Keyu An, Zhijian Ou, Chen Huang 외

Utilizing text-only data with an external language model (ELM) in end-to-end RNN-Transducer (RNN-T) for speech recognition is challenging. Recently, a class of methods such as density ratio (DR) and internal language mod…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers

2022-11-05 · Peidong Wang, Eric Sun, Jian Xue, Yu Wu 외

Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world application…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Identificationspeech-recognition+3

Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech

2022-05-10 · Ilya Sklyar, Anna Piunova, Christian Osendorfer

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the pre…

Segmentationspeech-recognitionSpeech RecognitionSpeech Separation+1

Exploring Neural Transducers for End-to-End Speech Recognition

2017-07-24 · Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates 외

In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer m…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition