Speech recognition method and related device

A speech recognition and speech frame technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of fine-grained phoneme modeling, pronunciation errors affecting recognition results, and difficulty in adapting speech recognition technology to speech recognition scenarios, achieving high fault tolerance. Ability, expand the effect of applicable scenarios

CN114360510APending Publication Date: 2022-04-15TENCENT TECH (SHENZHEN) CO LTD
7 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-04-15
Patent Text Reader

Abstract

The embodiment of the invention discloses a speech recognition method and a related device, and at least relates to a speech recognition technology in artificial intelligence, speech data to be recognized are used as input data of a time delay neural network in an acoustic model, and an output layer of the time delay neural network comprises acoustic modeling units corresponding to a plurality of syllables respectively, so that the speech recognition efficiency is improved. And the syllable probability distribution corresponding to the voice frames included in the voice data can be obtained by taking the syllables as the recognition granularity through the time delay neural network. When syllable recognition is carried out through the output layer, auxiliary judgment can be carried out on the syllables to which the voice frames belong on the basis of pronunciation rules in combination with front and back syllable information of the voice frames, so that more accurate syllable probability distribution is output. Moreover, since the syllables are generally composed of one or more phonemes, the method has higher fault-tolerant capability, not only can more accurately determine the speech recognition result based on the probability distribution of the syllables, but also has low requirements for the quality of the speech data to be recognized, and effectively expands the application scenarios of the speech recognition technology.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the field of speech recognition, in particular to a speech recognition method and related devices. Background technique

[0002] Speech recognition technology can provide users with voice content recognition services, and this technology can be applied in various scenarios, such as voice-to-text, voice wake-up, human-computer interaction and other scenarios. In a specific implementation, the acoustic features of the speech data to be recognized may be extracted through an acoustic model, and a corresponding speech recognition result may be determined based on the acoustic features.

[0003] Related technologies mainly use phone as the modeling unit of the acoustic model. A phoneme is the smallest unit of speech divided according to the natural properties of speech. It is analyzed based on the pronunciation actions in syllables. One action constitutes a phoneme.

[0004] However, the granularity of phoneme modeling is...

Examples

Embodiment Construction

[0030] Embodiments of the present application are described below in conjunction with the accompanying drawings.

[0031] When recognizing speech data, in related technologies, phonemes are used as the modeling unit of the acoustic model. For example, the phoneme sequence corresponding to the keyword "hello" is "niy3 hh aw3", and only the phoneme sequence "n iy3 hhaw3" to recognize the keyword "hello". Because the granularity of phoneme modeling is too fine, it requires high quality of speech data. If the pronunciation of one of the keywords is not standard, the recognition of the keyword will fail, resulting in a lower accuracy of the speech recognition results. The robustness of recognition is low, making speech recognition technology applicable to fewer scenarios.

[0032] Based on this, the embodiment of the present application provides a speech recognition method, which not only improves the accuracy of the speech recognition result, but also has lower requirements on t...