Towards large vocabulary ASR on embedded platforms
نویسنده
چکیده
In this paper we present an overview of an automatic speech recognition system implementation in the context of embedded systems. Specific challenges presented by low resource platforms will be addressed for the basic components of an ASR decoder. Our main objective is to utilize and modify the technology developed for large vocabulary ASR to achieve efficient LVCSR on embedded systems as well.
منابع مشابه
Semantic parsing using word confusion networks with conditional random fields
A challenge in large vocabulary spoken language understanding (SLU) is robustness to automatic speech recognition (ASR) errors. The state of the art approaches for semantic parsing rely on using discriminative sequence classification methods, such as conditional random fields (CRFs). Most dialog systems employ a cascaded approach where the best hypotheses from the ASR system are fed into the fo...
متن کاملLow complexity techniques for embedded ASR systems
This paper deals with the problem of reducing the computational complexity of ASR algorithms for embedded systems. Particularly, three methods for simplifying the computation of state observation likelihoods of continuous density based HMMs are proposed. Feature component masking, variable-rate partial likelihood update and density pruning all result in significant savings in the decoding compl...
متن کاملSpeech Recognition for Smart Homes
When Christopher Sholes created the QWERTY keyboard layout in the 1860s (often assumed to be for slowing down fast typists), few would have imagined that his invention would become the dominant input device of the 20th century. In the early years of the 21st century (the so called 'speed and information' century), its use remains dominant, despite many, arguably better, input devices having bee...
متن کاملProfiling large-vocabulary continuous speech recognition on embedded devices: a hardware resource sensitivity analysis
When deployed in embedded systems, speech recognizers are necessarily reduced from large-vocabulary continuous speech recognizers (LVCSR) found on desktops or servers to fit the limited hardware. However, embedded hardware continues to evolve in capability; today’s smartphones are vastly more powerful than their recent ancestors. This begets a new question: which hardware features not currently...
متن کاملLinguistically-motivated sub-word modeling with applications to speech recognition
Despite the proliferation of speech-enabled applications and devices, speech-driven human-machine interaction still faces several challenges. One of theses issues is the new word or the out-of-vocabulary (OOV) problem, which occurs when the underlying automatic speech recognizer (ASR) encounters a word it does not ”know”. With ASR being deployed in constantly evolving domains such as restaurant...
متن کامل