Share This Author
The LIMSI Broadcast News transcription system
The ETAPE corpus for the evaluation of speech-based TV content processing in the French language
- G. Gravier, G. Adda, Niklas Paulsson, Matthieu Carré, Aude Giraudel, Olivier Galibert
- Computer ScienceInternational Conference on Language Resources…
- 1 May 2012
The paper presents a comprehensive overview of existing data for the evaluation of spoken content processing in a multimedia framework for the French language. We focus on the ETAPE corpus which will…
Lightly supervised and unsupervised acoustic model training
Experiments providing supervision only via the language model training materials show that including texts which are contemporaneous with the audio data is not crucial for success of the approach, and that the acoustic models can be initialized with as little as 10 min of manually annotated data.
Last Words: Amazon Mechanical Turk: Gold Mine or Coal Mine?
To define precisely what MTurk is and what it is not, it is hoped that this will point out opportunities for the community to deliberately value ethics above cost savings.
Partitioning and transcription of broadcast news data
This paper reports on the recent work in transcribing broadcast news data, including the problem of partitioning the data into homogeneous segments prior to word recognition, using a Gaussian mixture models and an agglomerative clustering algorithm.
Where are we in transcribing French broadcast news?
Advances in automatic processing of broadcast news speech in French based on recent improvements to the LIMSI English system are described, with the main differences between the English and French BN systems being a 200k vocabulary to overcome the lower lexical coverage in French.
Investigating syllabic structures and their variation in spontaneous French
Breaking the Unwritten Language Barrier: The BULB Project
On designing pronunciation lexicons for large vocabulary continuous speech recognition
The American English lexicon developed primarily for the ARPA WSJ/NAB tasks is described, which is phonemically represented, and contains alternate pronunciations for about 10% of the words.
A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments
A speech corpus collected during a realistic language documentation process, made up of 5k speech utterances in Mboshi aligned to French text translations, is presented.