paper-with-me

홈 › Papers

LongFNT: Long-form Speech Recognition with Factorized Neural Transducer

2022-11-17 · Xun Gong, Yu Wu, Jinyu Li, Shujie Liu, Rui Zhao, Xie Chen, Yanmin Qian

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 attending longer transcription history for a vanilla neural transducer model shows no much gain in our preliminary experiments, since the prediction network is not a pure language model. This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor. We propose the {LongFNT-Text} architecture, which fuses the sentence-level long-form features directly with the output of the vocabulary predictor and then embeds token-level long-form features inside the vocabulary predictor, with a pre-trained contextual encoder RoBERTa to further boost the performance. Moreover, we propose the {LongFNT} architecture by extending the long-form speech to the original speech input and achieve the best performance. The effectiveness of our LongFNT approach is validated on LibriSpeech and GigaSpeech corpora with 19% and 12% relative word error rate~(WER) reduction, respectively.

📄 PDF Abstract BibTeX arXiv:2211.09412

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)FormLanguage ModelingLanguage ModellingSentencespeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Residual Connection 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer

2023-09-14 · Peng Wang, Yifan Yang, Zheng Liang, Tian Tan 외

Despite advancements of end-to-end (E2E) models in speech recognition, named entity recognition (NER) is still challenging but critical for semantic understanding. Previous studies mainly focus on various rule-based or a…

Language ModelingLanguage Modellingnamed-entity-recognitionNamed Entity Recognition+4

Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorization

2021-11-29 · Brian Yan, Chunlei Zhang, Meng Yu, Shi-Xiong Zhang 외

Conversational bilingual speech encompasses three types of utterances: two purely monolingual types and one intra-sententially code-switched type. In this work, we propose a general framework to jointly model the likelih…

speech-recognitionSpeech Recognition

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

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 외

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) mo…

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data

2017-09-22 · NeurIPS 2017 12 · Wei-Ning Hsu, Yu Zhang, James Glass

We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we exploit the multi-scale nature of infor…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speaker Verificationspeech-recognition+1