paper-with-me

Papers

A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation

2021-10-11 · Yosuke Higuchi, Nanxin Chen, Yuya Fujita, Hirofumi Inaguma, Tatsuya Komatsu, Jaesong Lee, Jumon Nozaki, Tianzi Wang, Shinji Watanabe

Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time applications, an increasing number of NAR models have been explored in different fields to mitigate the performance gap against AR models. In this work, we conduct a comparative study of various NAR modeling methods for end-to-end automatic speech recognition (ASR). Experiments are performed in the state-of-the-art setting using ESPnet. The results on various tasks provide interesting findings for developing an understanding of NAR ASR, such as the accuracy-speed trade-off and robustness against long-form utterances. We also show that the techniques can be combined for further improvement and applied to NAR end-to-end speech translation. All the implementations are publicly available to encourage further research in NAR speech processing.

📄 PDF Abstract BibTeX arXiv:2110.05249

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSpeech-to-TextText GenerationTranslation

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

Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding

2023-07-28 · Chunyu Qiang, Hao Li, Hao Ni, He Qu 외

Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks …

Language ModelingLanguage ModellingmodelSpeech Synthesis+2

Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study

2022-04-04 · Findings (ACL) 2022 5 · Serra Sinem Tekiroglu, Helena Bonaldi, Margherita Fanton, Marco Guerini

In this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English. We first present a comparative stu…

Automatic Post-EditingLanguage ModelingLanguage Modelling

Maximizing Mutual Information for Tacotron

2019-08-30 · Peng Liu, Xixin Wu, Shiyin Kang, Guangzhi Li 외

End-to-end speech synthesis methods already achieve close-to-human quality performance. However compared to HMM-based and NN-based frame-to-frame regression methods, they are prone to some synthesis errors, such as missi…

AttributeSpeech Synthesis

Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation

2021-05-11 · Findings (ACL) 2021 8 · Shun-Po Chuang, Yung-Sung Chuang, Chih-Chiang Chang, Hung-Yi Lee

We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to impro…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+3

Continuous Speech Synthesis using per-token Latent Diffusion

2024-10-21 · Arnon Turetzky, Nimrod Shabtay, Slava Shechtman, Hagai Aronowitz 외

The success of autoregressive transformer models with discrete tokens has inspired quantization-based approaches for continuous modalities, though these often limit reconstruction quality. We therefore introduce SALAD, a…

Image GenerationQuantizationSpeech Synthesistext-to-speech+1