paper-with-me

홈 › Papers

Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models

2022-12-05 · Rui Zhao, Jian Xue, Partha Parthasarathy, Veljko Miljanic, Jinyu Li

Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to mitigate this problem. The improved adaptation ability of FNT on text-only adaptation data came at the cost of lowered accuracy compared to the standard neural transducer model. We propose several methods to improve the performance of the FNT model. They are: adding CTC criterion during training, adding KL divergence loss during adaptation, using a pre-trained language model to seed the vocabulary predictor, and an efficient adaptation approach by interpolating the vocabulary predictor with the n-gram language model. A combination of these approaches results in a relative word-error-rate reduction of 9.48\% from the standard FNT model. Furthermore, n-gram interpolation with the vocabulary predictor improves the adaptation speed hugely with satisfactory adaptation performance.

📄 PDF Abstract BibTeX arXiv:2212.01992

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Factorized Neural Transducer for Efficient Language Model Adaptation

2021-09-27 · Xie Chen, Zhong Meng, Sarangarajan Parthasarathy, Jinyu Li

In recent years, end-to-end (E2E) based automatic speech recognition (ASR) systems have achieved great success due to their simplicity and promising performance. Neural Transducer based models are increasingly popular in…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+3

Improved Factorized Neural Transducer Model For text-only Domain Adaptation

2023-09-18 · Junzhe Liu, Jianwei Yu, Xie Chen

Adapting End-to-End ASR models to out-of-domain datasets with text data is challenging. Factorized neural Transducer (FNT) aims to address this issue by introducing a separate vocabulary decoder to predict the vocabulary…

DecoderDomain Adaptation

Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network

2021-04-22 · Janne Pylkkönen, Antti Ukkonen, Juho Kilpikoski, Samu Tamminen 외

Adaption of end-to-end speech recognition systems to new tasks is known to be challenging. A number of solutions have been proposed which apply external language models with various fusion methods, possibly with a combin…

Domain AdaptationLanguage ModelingLanguage ModellingPrediction+2

Effective internal language model training and fusion for factorized transducer model

2024-04-02 · Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide 외

The internal language model (ILM) of the neural transducer has been widely studied. In most prior work, it is mainly used for estimating the ILM score and is subsequently subtracted during inference to facilitate improve…

Language ModelingLanguage Modellingmodel

LongFNT: Long-form Speech Recognition with Factorized Neural Transducer

2022-11-17 · Xun Gong, Yu Wu, Jinyu Li, Shujie Liu 외

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply at…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)FormLanguage Modeling+4