Those goals were to employ automatic speech recognition and information retrieval techniques to provide improved access to the large video archive containing recorded testimonies of the Holocaust survivors.
For example, machine learning on ranking (also called ordinal regression) and reranking has been applied to many tasks, such as speech recognition [28], [29], information extraction [30], [31], information retrieval [32], [33], question answering [34], syntactic parsing [35] [37], machine translation [38], [39], and gene prediction [40].
This automatic segmentation system can be easily integrated into an automatic continuous speech recognition system, where information about individual acoustic segments can be used for acoustic model selection and adaptation, or as additional information for rich transcription output.
The idea, according to them, "was to use Indian language speech recognition to deliver information and access to the unconnected billion or so people and give them opportunities to drive economic growth".
It is well known that the FFT-based MFCC, and almost all other features conventionally used for speech recognition, discard pitch information and can not track the fast-changing events in speech signals.
When working with SYNC-enabled smartphone apps, developers are able to create a voice user interface using SYNC's in-vehicle speech recognition system, write information to the radio head display or in-vehicle touch screen, using the text-to-speech engine, the in-vehicle meny system to provide commands for their mobile app, and vehicle data, like speed, GPS location, and fuel economy.
This finding prompted the proposal of the MALACH project (Multilingual Access to Large Spoken Archives--years 2002-2007) whose aim was to use automatic speech recognition (ASR) and information retrieval techniques for access to the archive and thus circumvent the need for manual annotation and cataloging.
The IVR uses algorithms and speech recognition to collect information from participants and monitor symptoms.
Their use gradually moved from augmentation of speech recognition systems with visual information [1], to recognition tasks in video where models are trained on video features alone [2].
