rttlesnke

Mostly, no Linux support. I really want an open iTunes alternative which runs on Linux or any Unix, and can re-encode my entire music library with the codec/bitrate I want, while retaining music metadata. iTunes is good at that. Opus/Ogg support would be great. Anyone know of something like this?

A short overview of using HMMs for speech recognition:

Speech is temporal, a speech sample can be represented as a sequence of data points. Thus, a simple way to compare two speech samples can be an algorithm to compare their corresponding sequences. One such algorithm is DTW, which is an equivalent of the Levenshtein distance algorithm for comparing strings.

So now we have a method of comparing two speech samples. Thus, a simple way to recognize an unknown speech sample can be to keep samples of all possible utterances (phonemes, words, sentences) and just return the best match. That’s not possible - so in speech recognition, they only keep samples of phonemes, and try to find the most likely concatenation of them relative to the unknown sample. The search space is huge, but luckily dynamic programming algorithms exist to make the search fast (they’re called Connected Word Recognition algorithms).

The problem with this approach is that it does not scale. There are tons of variations possible for the same spoken unit (different styles and durations). This is where the Hidden Markov Model comes in. A single HMM can be used to represent all variations of that unit. For example, it can be used to represent multiple speech samples of the word “apple”, or of the phoneme “æ” and so on. There are methods for evaluating the similarity of an HMM and a speech sample, and for training an HMM using multiple samples.

You can also connect phoneme HMMs together to get a big HMM representing words/sentences. The same CWR algorithms as before apply.

I've been studying HMMs lately. I think getting an initial estimate of HMM emission and transition parameters using Segmental K-means training (or Viterbi training) before applying Baum-Welch re-estimation should result in the latter converging better. That's what the HInit tool in HTK does. AFAIK, it's done in the following way:

- Divide all examples (observation sequences) uniformly into as many segments as the number of states.

- Cluster the observations corresponding to each state, and estimate the GMM using the cluster set so that each cluster corresponds to one multivariate Gaussian.

- Do this repeatedly until convergence: get the Viterbi alignment of all examples, use it to get new segments, and estimate the parameters again using the previous step.

Please correct me if I'm wrong. Also, I have two questions:

- What kind of accuracy increase should be expected if using both Viterbi training and Baum-Welch re-estimation, instead of just the latter?

- What kind of accuracy should be expected if only using Viterbi training?

As a person who thinks the opposite, this comes as a shock to me. Care to explain?

This is exactly what I want too. Pocket-sized tablets may have their advantages, but the compact size of the iPhone is more attractive to me. Make an Android flagship phone of that size, that'd be #1 on my list.