Following the first successful edition of the Workshop on Speech, Language and Audio in Multimedia (SLAM) in Marseille, France, we will be bringing the next edition of the workshop to Penang, Malaysia. SLAM workshop aims at bringing together researchers working in speech, language and audio processing to analyze, index and access multimedia data. Multimedia data are now available in very large amounts: Lectures, meetings, interviews, debates, conversational broadcast, podcasts, social videos on the Web, etc. Such data, along with the associated use scenarios, raise specific challenges: Robustness facing the high variability in quality; Efficiency to handle very large amount of data; Semantics shared across modalities; Potentially high error rates in transcription; etc. Worldwide, several national and international research projects are focusing on audio analysis of multimedia data. Similarly, various benchmark initiatives have been initiated such as TRECVID MED, MediaEval, or ETAPE and REPERE in France.

The SLAM workshop intends to bring together players from the field to share recent research results, discuss ongoing and future projects, benchmarking initiatives and applications. We expect communications on research work, project description, evaluation initiative, demonstrations and applications dealing with speech and/or language and/or audio on any type of multimedia material. The list of topics of interest includes (but is not limited to):
● Audio event detection and audio classification
● Speech and speaker recognition on multimedia material
● Audio-aware genre analysis and classification
● Multimodal speaker identification and clustering
● Multimedia spoken term detection and content retrieval
● Speech and audio aware content segmentation and structuring
● Audio indexing and fingerprinting
● Robust feature extraction and processing
● Natural language processing for multimedia
● Metadata extraction: Entity extraction, keyword extraction, etc.
● Summarization and hyperlink generation
● Multimodal fusion and integration involving audio
● Generation of descriptive text for multimedia
● Speech and audio multimedia applications and services
● Databases and benchmarks
● Large scale speech and audio analysis
● Navigation in multimedia audio content applied to any media such as:
● Professional broadcasts – TV, radio, podcasts, newsfeeds, synopsis, etc.
● Social media – YouTube, Flickr, Facebook, Twitter, Voice Social Network, etc.
● Audiovisual archives – Lectures and conferences, meetings, etc.
● Music – Music catalogs, music collections, etc.
● Affective and behavioural analytics based on multimodal cues

SLAM 2014 is organized in conjunction with Interspeech 2014 over 1.5 days, starting Thu. 11 Sept. 2014 and ending Fri. 12 Sept. 2014 afternoon. Penang is conveniently connected by bus, train and flight to Singapore, where the Interspeech 2014 conference will take place. The format of the workshop will include an invited talk, oral presentations of scientific work and a poster session for project and benchmark presentations.

Important dates:
Full paper submission deadline: June 12, 2014
Notification of acceptance: July 16, 2014
Camera ready paper: July 31, 2014
Early bird registration: August 7, 2014
SLAM workshop: September 11-12, 2014

SLAM 2014 Workshop is jointly organized by the ISCA SIG on Speech and Language in Multimedia and the IEEE SIG on Audio and Speech Processing in Multimedia.