paper-with-me

Papers

Conformer-based Hybrid ASR System for Switchboard Dataset

2021-11-05 · Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Wilfried Michel, Alexander Gerstenberger, Ralf Schlüter, Hermann Ney

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using conformer acoustic model for hybrid ASR is not investigated. In this paper, we present and evaluate a competitive conformer-based hybrid model training recipe. We study different training aspects and methods to improve word-error-rate as well as to increase training speed. We apply time downsampling methods for efficient training and use transposed convolutions to upsample the output sequence again. We conduct experiments on Switchboard 300h dataset and our conformer-based hybrid model achieves competitive results compared to other architectures. It generalizes very well on Hub5'01 test set and outperforms the BLSTM-based hybrid model significantly.

📄 PDF Abstract BibTeX arXiv:2111.03442

Code (0)

등록된 구현이 없습니다.

Tasks

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

Similar Papers 제목 키워드 기반

Improving the Training Recipe for a Robust Conformer-based Hybrid Model

2022-06-26 · Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Ralf Schlüter 외

Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based on feature-space approaches for a conform…

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

Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems

2022-06-23 · Mingyu Cui, Jiajun Deng, Shoukang Hu, Xurong Xie 외

Fundamental modelling differences between hybrid and end-to-end (E2E) automatic speech recognition (ASR) systems create large diversity and complementarity among them. This paper investigates multi-pass rescoring and cro…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Diversityspeech-recognition+1

Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers

2021-07-07 · Huahuan Zheng, Wenjie Peng, Zhijian Ou, Jinsong Zhang

Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficien…

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

Analyzing And Improving Neural Speaker Embeddings for ASR

2023-01-11 · Christoph Lüscher, Jingjing Xu, Mohammad Zeineldeen, Ralf Schlüter 외

Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated the usage of neural speaker embeddings fo…

Speaker Verification

On the limit of English conversational speech recognition

2021-05-03 · Zoltán Tüske, George Saon, Brian Kingsbury

In our previous work we demonstrated that a single headed attention encoder-decoder model is able to reach state-of-the-art results in conversational speech recognition. In this paper, we further improve the results for …

DecoderEnglish Conversational Speech RecognitionLanguage ModelingLanguage Modelling+2