The LIMSI Broadcast News transcription system
By Jean-Luc Gauvain, Lori Faith Lamel, Gilles Adda. Speech Communication, 2002
504 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Signal Processing
View Paper: https://www.semanticscholar.org/paper/94f70b874913d65bdad1be4061e794b485457e77
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Dong Yu
- James R. Glass
- Tara N. Sainath
- Li Deng
- Jinyu Li
- Yoshua Bengio
- Bhuvana Ramabhadran
- Yonatan Belinkov
In Signal Processing
- Dong Yu
- Tara N. Sainath
- James R. Glass
- Bhuvana Ramabhadran
- Jinyu Li
- Li Deng
- Cees G. M. Snoek
- Marcel Worring
Citations in the corpus
- Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR (2011, methodology): “The language model used for decoding is a 54M n-gram, interpolated backoff model trained on a collection of 335M words.”
- Concept-Based Video Retrieval (2009, methodology): “For this first TRECVID cycle, LIMSI [62] donated automatic speech recognition results, and CLIPS-IMAG [187] provided the camera shot segmentation and associated key frames.”
- Early versus late fusion in semantic video analysis (2005, methodology): “The LIMSI broadcast news transcription system.”
- Optimizing bottle-neck features for lvcsr (2008, methodology): “The recognition system is a development version of the Arabic speech-to-text used in the AGILE participation in the GALE’07 evaluation [11, 12].”
- Unsupervised Pattern Discovery in Speech (2008, background): “O VER the last several decades, significant progress has been made in developing automatic speech recognition (ASR) systems which are now capable of performing large-vo-cabulary continuous speech recognition [1], [2].”
- Continuous space language models (2007, background): “A detailed description of the technology that is common to all speech recognizers can be found in Gauvain et al. (2002).”
- Connectionist language modeling for large vocabulary continuous speech recognition (2002, methodology): “The speech recognizer used in these experiments was derived from the LIMSI broadcast news transcription system[6].”
- A Multimodal Scheme for Program Segmentation and Representation in Broadcast Video Streams (2008, methodology): “Fairly various programs, dramatic content changes in lighting, chromatic composition and creative stories have made existing shot-level [11], [12], or scene-level [4]–[9] structuring or genre categorization [13]–[20] methods less effective for program segmentation and subsequent manipulation and…”