On Language Model Integration for RNN Transducer based Speech Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
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 RecognitionAn Empirical Study of Language Model Integration for Transducer based Speech Recognition
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 RecognitionLAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers
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+3Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech
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+1Exploring Neural Transducers for End-to-End Speech Recognition
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