TED-LIUM: an Automatic Speech Recognition dedicated corpus
This paper presents the corpus developed by the LIUM for Automatic Speech Recognition (ASR), based on the TED Talks. This corpus was built during the IWSLT 2011 Evaluation Campaign, and is composed of 118 hours of speech with its accompanying automatically aligned transcripts. We describe the content of the corpus, how the data was collected and processed, how it will be publicly available and how we built an ASR system using this data leading to a WER score of 17.4 {\%}. The official results we obtained at the IWSLT 2011 evaluation campaign are also discussed.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language Modellingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation
In this paper, we present TED-LIUM release 3 corpus dedicated to speech recognition in English, that multiplies by more than two the available data to train acoustic models in comparison with TED-LIUM 2. We present the r…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionThe MeMAD Submission to the IWSLT 2018 Speech Translation Task
This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated on…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationNMT+3Privacy attacks for automatic speech recognition acoustic models in a federated learning framework
This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially imp…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Federated Learningspeech-recognition+1The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation
This paper describes our work in participation of the IWSLT-2021 offline speech translation task. Our system was built in a cascade form, including a speaker diarization module, an Automatic Speech Recognition (ASR) modu…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeaker-diarization+4LV-CTC: Non-autoregressive ASR with CTC and latent variable models
Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist tempo…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+1