Geographical name speech signal recognition method based on continuous Gaussian mixture HMM models (hidden Markov models)

Abstract

The invention discloses a geographical name speech signal recognition method based on continuous Gaussian mixture HMM models (hidden Markov model), wherein a process of training the continuous Gaussian mixture HMM model comprises the following steps: defining and initializing the HMM models; putting a characteristic matrix of a category of geographical name speech signals into the models and conducting training; calculating a probability that the category of geographical name speech signals appear in accordance with model parameters; comparing the probability with an output probability before the training is conducted, and judging whether a relative error satisfies output conditions or not; if so, outputting the HMM model corresponding to the category of geographical name speech signals; if not, judging whether training times reach a maximum training threshold or not; conducting the training once again when the training times fail to reach the maximum training threshold, or outputting the HMM models when the training times reach the maximum training threshold; and putting characteristic matrices of the various categories of geographical name speech signals into the models so as to obtain a plurality of HMM models corresponding to different geographical names, so that a geographical name speech recognition model library is formed. With the application of the geographical name speech signal recognition method provided by the invention, the HMM models, which are applicable to geographical name speech recognition of isolate words, as well as the geographical name speech recognition model library can be obtained, so that conditions are created for conducting geographical name speech recognition accurately.

Description

technical field

[0001] The invention relates to a place name speech signal recognition method, in particular to a place name speech signal recognition method based on a continuous mixed Gaussian HMM model. Background technique

[0002] With the rapid development of the economy and the increasingly prominent trend of globalization, the modern logistics industry has achieved unprecedented development in developed countries, and has produced huge economic and social benefits. Logistics resources include transportation, warehousing, sorting, packaging, Distribution, etc. These resources are scattered in multiple fields, including manufacturing, agriculture, distribution, etc.

[0003] In the sorting process, sorting is basically carried out manually at this stage. Since the workers are in a noisy working environment for a long time, they will inevitably have a certain sense of fatigue in their minds and bodies, and the singleness and repetition of work tasks will also make Thei...

Examples

Embodiment Construction

[0046] Objects, advantages and features of the present invention will be illustrated and explained by the following non-limiting description of preferred embodiments. These embodiments are only typical examples of applying the technical solutions of the present invention, and all technical solutions formed by adopting equivalent replacements or equivalent transformations fall within the protection scope of the present invention.

[0047] The present invention discloses a place name speech signal recognition method based on a continuous mixed Gaussian HMM model, including the training process of the continuous mixed Gaussian HMM model and the place name speech recognition process, wherein, as attached figure 1 As shown, the training process of the continuous mixed Gaussian HMM model is as follows:

[0048] S1, define a continuous mixed Gaussian HMM model containing the following parameters, λ=(N, M, A, π, B), where:

[0049] N, the number of model states, is 4;

[0050] M, th...

technical field

[0001] The invention relates to a place name speech signal recognition method, in particular to a place name speech signal recognition method based on a continuous mixed Gaussian HMM model. Background technique

[0002] With the rapid development of the economy and the increasingly prominent trend of globalization, the modern logistics industry has achieved unprecedented development in developed countries, and has produced huge economic and social benefits. Logistics resources include transportation, warehousing, sorting, packaging, Distribution, etc. These resources are scattered in multiple fields, including manufacturing, agriculture, distribution, etc.

[0003] In the sorting process, sorting is basically carried out manually at this stage. Since the workers are in a noisy working environment for a long time, they will inevitably have a certain sense of fatigue in their minds and bodies, and the singleness and repetition of work tasks will also make Thei...

Examples

Embodiment Construction

[0046] Objects, advantages and features of the present invention will be illustrated and explained by the following non-limiting description of preferred embodiments. These embodiments are only typical examples of applying the technical solutions of the present invention, and all technical solutions formed by adopting equivalent replacements or equivalent transformations fall within the protection scope of the present invention.

[0047] The present invention discloses a place name speech signal recognition method based on a continuous mixed Gaussian HMM model, including the training process of the continuous mixed Gaussian HMM model and the place name speech recognition process, wherein, as attached figure 1 As shown, the training process of the continuous mixed Gaussian HMM model is as follows:

[0048] S1, define a continuous mixed Gaussian HMM model containing the following parameters, λ=(N, M, A, π, B), where:

[0049] N, the number of model states, is 4;

[0050] M, th...

Images