SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain

2023-01-08 · Heli Qi, Sashi Novitasari, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

This paper introduces SpeeChain, an open-source Pytorch-based toolkit designed to develop the machine speech chain for large-scale use. This first release focuses on the TTS-to-ASR chain, a core component of the machine speech chain, that refers to the TTS data augmentation by unspoken text for ASR. To build an efficient pipeline for the large-scale TTS-to-ASR chain, we implement easy-to-use multi-GPU batch-level model inference, multi-dataloader batch generation, and on-the-fly data selection techniques. In this paper, we first explain the overall procedure of the TTS-to-ASR chain and the difficulties of each step. Then, we present a detailed ablation study on different types of unlabeled data, data filtering thresholds, batch composition, and real-synthetic data ratios. Our experimental results on train_clean_460 of LibriSpeech demonstrate that our TTS-to-ASR chain can significantly improve WER in a semi-supervised setting.

📄 PDF Abstract BibTeX arXiv:2301.02966

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationGPU

ESPnet-ST: All-in-One Speech Translation Toolkit

2020-04-21 · ACL 2020 6 · Hirofumi Inaguma, Shun Kiyono, Kevin Duh, Shigeki Karita 외

We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework. ESPnet-ST is a new project inside end-to-end speech processing toolkit, ESPnet, which integ…

All Automatic Speech Recognition Automatic Speech Recognition (ASR)Machine Translation+6

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

2023-05-18 · Zhifu Gao, Zerui Li, JiaMing Wang, Haoneng Luo 외

This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and…

Action Detection Activity Detection speech-recognition Speech Recognition

CNTK: Microsoft's Open-Source Deep-Learning Toolkit

2016-08-01 · ACM SIGKDD 2016 8 · Frank Seide, Amit Agarwal

This tutorial will introduce the Computational Network Toolkit, or CNTK, Microsoft's cutting-edge open-source deep-learning toolkit for Windows and Linux. CNTK is a powerful computation-graph based deep-learning toolkit …

Clustering Deep Learning Dimensionality Reduction General Classification+2

XNMT: The eXtensible Neural Machine Translation Toolkit

2018-03-01 · WS 2018 3 · Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix 외

This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distin- guishes itself from other open-source NMT toolkits by its focus on modular code design, with the purpose of enabling fast iterati…

Machine Translation NMT speech-recognition Speech Recognition+1

Espresso: A Fast End-to-end Neural Speech Recognition Toolkit

2019-09-18 · Yiming Wang, Tongfei Chen, Hainan Xu, Shuoyang Ding 외

We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq.…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Data Augmentation Decoder+6