Robust Speech Recognition Using Neural Networks and Hidden Markov Models
ITCC '00 Proceedings of the The International Conference on Information Technology: Coding and Computing (ITCC'00)
Automatic speech recognition and speech variability: A review
Speech Communication
Hi-index | 0.00 |
We present a connected digit recognition system with low storage and computational complexity which achieves good performance in car noise. Our system uses the TI-DIGITS database with additive car noise for training whole-word digit and background models. A digit accuracy of 96.1% is obtained on a 15-speaker database collected in a car using an open microphone with an average SNR of approximately 2 dB. There is a further error reduction of almost 35% if the top two candidate strings are considered using a traceback based N-best algorithm. The system can be implemented on a currently available fixed-point DSP chip. We show that significant performance improvements are obtained by using two-level cepstral mean subtraction (CMS), gender-dependent models and a decoding grammar constraining the possible lengths of digit strings.