• ESPnet

  • Referenced in 6 articles [sw32059]
  • automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and PyTorch ... learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format ... which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ... ASR benchmarks...
  • LibriSpeech

  • Referenced in 9 articles [sw35386]
  • LibriSpeech ASR corpus: LibriSpeech is a corpus of approximately 1000 hours of 16kHz read English...
  • Espresso

  • Referenced in 3 articles [sw39131]
  • neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch ... features various decoding approaches commonly employed in ASR, including look-ahead word-based language model ... implemented. Espresso achieves state-of-the-art ASR performance on the WSJ, LibriSpeech, and Switchboard...
  • Conformer

  • Referenced in 4 articles [sw35794]
  • shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models...
  • RASR

  • Referenced in 2 articles [sw26581]
  • RWTH ASR - The RWTH Aachen University Speech Recognition System. RWTH ASR (short ”RASR...
  • MLS

  • Referenced in 2 articles [sw38352]
  • Models (LM) and baseline Automatic Speech Recognition (ASR) models and for all the languages ... transcribed dataset will open new avenues in ASR and Text-To-Speech (TTS) research...
  • k2

  • Referenced in 2 articles [sw39144]
  • fast implementation of decoding for ASR, and for CTC and LF-MMI training. This ... extensible framework to allow further development of ASR technology...
  • CrossASR++

  • Referenced in 1 article [sw38715]
  • ensure the quality of Automatic Speech Recognition (ASR) systems. However, manually collecting required test cases ... proposes CrossASR, a differential testing method for ASR systems. This method first utilizes Text ... then feed these audios into different ASR systems for cross-referencing to uncover failed test ... increase by leveraging more advanced TTS and ASR systems. So in this accompanying tool demo...
  • PyChain

  • Referenced in 1 article [sw35385]
  • ASR. We present PyChain, a fully parallelized PyTorch implementation of end-to-end lattice-free ... models} in the Kaldi automatic speech recognition (ASR) toolkit. Unlike other PyTorch and Kaldi based ... ASR toolkits, PyChain is designed to be as flexible and light-weight as possible ... easily plugged into new ASR projects, or other existing PyTorch-based ASR tools, as exemplified...
  • ASR

  • Referenced in 1 article [sw38328]
  • automated workflows. The Atomic Simulation Recipes (ASR) is an open source Python framework for working ... suited for high-throughput projects. Central to ASR is the concept of a Recipe ... keeping track of the data provenance. The ASR leverages the functionality of the Atomic Simulation ... freedom for users to build advanced workflows. ASR also implements a command line interface that...
  • ExKaldi-RT

  • Referenced in 1 article [sw38118]
  • remarkable role in automatic speech recognition (ASR). Kaldi, for instance, is widely used to develop ... state-of-the-art offline and online ASR systems. This paper describes the ”ExKaldi ... online ASR toolkit implemented based on Kaldi and Python language. ExKaldi-RT provides tools ... easy-to-use interface for online ASR system developers to exploit original research, for example...
  • ExKaldi

  • Referenced in 1 article [sw38120]
  • developed to build an interface between Kaldi ASR toolkit and Python. Differing from other Kaldi ... these features: Integrated APIs to build a ASR systems, including feature extraction, GMM-HMM acoustic ... help developers build high-performance ASR systems with Python language easily...
  • SLURP

  • Referenced in 2 articles [sw36137]
  • state-of-the-art NLU and ASR systems; (3) A new transparent metric for entity...
  • Libri-Light

  • Referenced in 2 articles [sw39141]
  • Libri-Light: A Benchmark for ASR with Limited or No Supervision. We introduce...
  • GigaSpeech

  • Referenced in 2 articles [sw40419]
  • GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio. This...
  • WeNet

  • Referenced in 1 article [sw37166]
  • WeNet provides an efficient way to ship ASR applications in several real-world scenarios, which...
  • NARA-WPE

  • Referenced in 1 article [sw38160]
  • recognition performance of downstream automatic speech recognition (ASR). It is suitable both for single-channel...
  • darch

  • Referenced in 306 articles [sw11086]
  • darch: Package for deep architectures and Restricted-Bolzmann...
  • Python

  • Referenced in 2049 articles [sw14460]
  • Python is a widely used high-level, general...