A study of speech recognition system robustness to microphone variations
نویسندگان
چکیده
This study seeks to improve our understanding of the e ects of microphone variations on speech recognition systems. The timit corpus provides data recorded on close talking and far eld microphones and over telephone lines. The summit system is con gured for phonetic classi cation and recognition. At the last icslp, we presented an analysis of the data and experiments in phonetic classi cation using a baseline system and various preprocessing techniques. In this paper, we present experiments in phonetic recognition using an improved baseline system and compensation techniques that require varying amounts of microphone speci c data.
منابع مشابه
Persian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملHigh Performance Speech Recognition Using Consistency Modeling
The primary goal of this project is to develop acoustic roodcling techniques that advance the state-of-the-art in speech recognition, focusing on those techniques that relax the hidden Markov model's improper independence assumptions. Such techniques should both improve robustness to systematic variations such as microphone, channel, and speaker, by conditioning state's acoustic output distribu...
متن کاملHistogram Equalization for Robust Speech Recognition
Optimal Automatic Speech Recognition takes place when the evaluation is done under circumstances identical to those in which the recognition system was trained. In the speech applications demanded in the actual real world this will almost never happen. There are several variability sources which produce mismatches between the training and test conditions. Depending on his physical or emotional ...
متن کاملIncreasing robustness in GMM speaker recognition systems for noisy and reverberant speech with low complexity microphone arrays
In this paper we describe the additive robustness obtained through the combined use of a first acoustic processing step based on a low complexity microphone array, followed by a spectral normalization step. Microphone arrays have shown to provide good results in reducing different sources of acoustic degradation. However, microphone arrays produce linear filtering effects that need to be compen...
متن کاملImproving Microphone Array Speech Recognition with Cochlear Implant-like Spectrally Reduced Speech
Cochlear implant-like spectrally reduced speech (SRS) has previously been shown to afford robustness to additive noise. In this paper, it is evaluated in the context of microphone array based automatic speech recognition (ASR). It is compared to and combined with post-filter and cepstral normalisation techniques. When there is no overlapping speech, the combination of cepstral normalization and...
متن کامل