Autodirective Microphone Systems for Natural Communication with Speech Recognizers
نویسندگان
چکیده
Two technological advances support new sophistication in sound capture; namely, high-quality lowcost electret microphones and high-speed economical signal processors. Combined with new understanding in acoustic beamforming, these technologies permit spatially-selective transduction of speech signals several octaves in bandwidth. Spatial selectivity mkigates the effects of noise and reverberation, and digital processing provides the capability for speechseeking, autodirective performance. This report outlines the principles of autodirective beamforming for acoustic arrays, and it describes two experimental implementations. It also summarizes the direction and emphasis of continuing research.
منابع مشابه
Microphone Arrays and Neural Networks for Robust Speech Recognition
This paper explores use of synergistically-integrated systems of microphone arrays and neural networks for robust speech recognition in variable acoustic environments, where the user must not be encumbered by microphone equipment. Existing speech recognizers work best for "high-quality close-talking speech." Performance of these recognizers is typically degraded by environmental interference an...
متن کاملRecognition of Prosodic Factors and Detection of Landmarks for Improvements to Continuous Speech Recognition Systems
This thesis examines the usefulness of including prosodic and phonetic context information in the phoneme model of a speech recognizer. This is done creating a series of prosodic and phonetic models and then comparing the log likelihoods of each model. The comparison of log likelihoods shows that both prosodic and phonetic context information improve the phoneme model for most phonemes. The pro...
متن کاملAutomatic Speech Recognition and Speech Activity Detection in the CHIL Smart Room
An important step to bring speech technologies into wide deployment as a functional component in man-machine interfaces is to free the users from close-talk or desktop microphones, and enable far-field operation in various natural communication environments. In this work, we consider far-field automatic speech recognition and speech activity detection in conference rooms. The experiments are co...
متن کاملAccurate consonant perception without mid-frequency speech energy
The intelligibility of consonants remains high (roughly 90% correct) for untrained human listeners when speech energy in the mid-frequencies (800 to 4 kHz) is filtered out of random CVC nonsense syllables using sharp high-pass and low-pass filters. These results suggest that humans are using a process for speech recognition that is fundamentally different from the types of template matching per...
متن کاملReal-Time Speaker Verification with a Microphone Array
Real-time speaker verification, with speech acquired using the NIST Mk-III microphone array and an autodirective beamforming algorithm, is demonstrated. The software and hardware backbone of the demonstration is the NIST Smart Flow System and Mk-III Array, both developed by National Institute of Standards and Technology in support of multimodal research communities. A microphone array acquires ...
متن کامل