next up previous
Next: Integrating Artificial Neural Networks Up: Speech Recognition with HMMs Previous: Imbalance Between Emission and

Unrealistic Probabilistic Assumptions in Speech HMMs

 

In this section, we briefly discuss the main unrealistic probabilistic assumptions behind state-of-the-art speech recognition systems based on HMMs. Although these problems have been known for many years, and much research has been done to address these problems, this research has not yielded significantly improved recognition performance.

  1. The HMM topology (which is very sparse) imposes a very strong a-priori on the meaning of the state variable, which is typically not realistic. In particular it does not take into account many possible effects of context (and this is related to several of the problems below).
  2. Some important long-term structure is not taken into account, such as, the identity of the speaker (which induces a dependency on the consecutive observations from the same speaker), and prosody (which represents the slow-varying sequential structure of pitch, duration, and energy).
  3. The modeling of durations is generally not realistic (see also the problem of imbalance between emission and transition probabilities which results in speech recognition not taking much account of the duration model incorporated in non-zero transition probabilities, section 3.6).
  4. Consecutive acoustic vectors are not conditionally independent (given the state). This is in fact often forced on the data sequence by using in the observation vector for each time step information that overlaps with that in neighboring time steps (e.g., using first and second time-derivatives of the spectral or cepstral coefficients).
  5. The acoustic features used as observations do not contain all the relevant information from the speech (typically most systems use cepstral coefficients, obtained from a short-term power spectrum).



Yoshua Bengio
Tue Oct 7 08:34:36 EDT 1997