No abstract

Gaussian Mixture Models (GMM) are a widespread tool in applications like speaker identification or verification. In contrast to Hidden Markov Models (HMM) Gaussian Mixture Models are designed to model the general properties of an underlying acoustic source. In our paper we extend the application of GMMs to the assessment of speaking rate. Directly trained on the acoustic data, they can be either applied directly to estimate the speech rate category orwith the help of a mapping functionthey can provide a continuous measure for the speaking rate. The mapping function can be realized by means of a Neural Net. First experiments showed a correlation coefficient of 0.66 between the lexical phoneme rate and our estimation based on speech rate dependent spectral variation. Moreover, our approach can be used simultaneously for high accuracy on-line gender detection.

Keyword spotting is a very forward-looking and promising branch of speech recognition. This paper presents a HMM-based keyword spotting system, which works with a new algorithm.The first discussion topic is the description of the search algorithm, that needs no representation of the non-keyword parts of the speech signal. For this purpose, the computation of the HMM scores and the Viterbi algorithm had to be modified. The keyword HMMs are not concatenated with other HMMs, so that there is no necessity for filler or garbage models. As a further advantage, this algorithm needs only low computional expense and storage requirement.The second discussion topic is the determination of a optimal decision threshold for each keyword. In order two decide between the two possibilities "keyword was spoken" and "keyword was not spoken", the scores of the keywords are compared with keyword specific decision thresholds. This paper introduces a method to fix decision thresholds in advance. Starting with measured phoneme distributions, the score distributions of whole keyword models can be calculated. Furthermore, these keyword distributions form the basis of the computation of decision thresholds.Tests with spontaneous speech databases yielded 73.9% Figure-OfMerit when using context-dependent HMMs. The detection rate at 10 fa/kw/h comes to 80%.

No abstract

No abstract