Enhancement of connected words in an extremely noisy environment

• Published in: IEEE transactions on speech and audio processing Vol. 5; no. 2; pp. 141 - 148
• Main Authors: Cohen, Y., Erell, A., Bistritz, Y.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.1997; Institute of Electrical and Electronics Engineers
• Subjects: Additive noise; Applied sciences; Automatic speech recognition; Degradation; Exact sciences and technology; Hidden Markov models; Information, signal and communications theory; Mean square error methods; Noise level; Signal processing; Signal to noise ratio; Speech enhancement; Speech processing; Speech recognition; Telecommunications and information theory; Working environment noise; Additive noise; Performance evaluation; Error estimation; Least squares method; Noise reduction; Speech recognition; Markov model; Algorithm; Speech processing
• ISSN: 1063-6676
• DOI: 10.1109/89.554776

A speech enhancement algorithm that is based on a connected-word hidden Markov model (HMM) is developed. Speech is assumed to be highly degraded by statistically independent additive noise. The minimum mean square error estimator is derived for a connected-word HMM. Further, we derive an estimator based on a connected-word HMM with explicit state duration. Listening experiments performed with digit strings have shown an increase of intelligibility. The best results were achieved when subjects who listened to the enhanced speech were given the results of an automatic recognition system.