CONF weber-ar-00-30/IDIAP HMM2- A Novel Approach to HMM Emission Probability Estimation Weber, Katrin Bengio, Samy Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2000/rr00-30.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/weber-rr-00-30 Related documents International Conference on Spoken Langugae Processing (ICSLP 2000) 2000 Beijing, China October 2000 III.147-150 IDIAP-rr 00-30 In this paper, we discuss and investigate a new method to estimate local emission probabilities in the framework of hidden Markov models (HMM). Each feature vector is considered to be a sequence and is supposed to be modeled by yet another HMM. Therefore, we call this approach `HMM2'. There is a variety of possible topologies of such HMM2 systems, e.g. incorporating trellis or ergodic HMM structures. Preliminary HMM2 speech recognition experiments on cepstral and spectral features yielded worse results than state-of-the-art systems. However, we believe that HMM2 systems have a lot of potential advantages and are therefore worth investigating further. REPORT weber-rr-00-30/IDIAP HMM2- A Novel Approach to HMM Emission Probability Estimation Weber, Katrin Bengio, Samy Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2000/rr00-30.pdf PUBLIC Idiap-RR-30-2000 2000 IDIAP Martigny, Switzerland Published: ICSLP 2000, Beijing, October 2000 In this paper, we discuss and investigate a new method to estimate local emission probabilities in the framework of hidden Markov models (HMM). Each feature vector is considered to be a sequence and is supposed to be modeled by yet another HMM. Therefore, we call this approach `HMM2'. There is a variety of possible topologies of such HMM2 systems, e.g. incorporating trellis or ergodic HMM structures. Preliminary HMM2 speech recognition experiments on cepstral and spectral features yielded worse results than state-of-the-art systems. However, we believe that HMM2 systems have a lot of potential advantages and are therefore worth investigating further.