An elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector construction and an appropriate selection of the classifier were sought. The experimental research was conducted on the basis of a spoken corpus in which speech was represented both acoustically and visually. The extracted features represented three types: geometrical, textural and mixed ones. The features were processed employing the classification algorithms based on Hidden Markov Models and Sequential Minimal Optimization. Tests were carried out employing the processed video material recorded with English native speakers who read specially prepared list of commands. The obtained results are discussed in the paper.

/pdf/a-comparative-study-of-english-viseme-recognition-methods-20r14vlxpx.pdf

A comparative study of English viseme recognition methods and algorithms

语言学综览 : [英文版] = The Handbook of Linguistics

People with articulation and phonological disorders need exercise to execute sounds of speech. Essentially, exercise starts with production of non-articulatory sounds in clinics or homes where a huge variety of the environment sounds exist; i.e., in noisy locations. Speech recognition systems considers environment sounds as background noises, which can lead to unsatisfactory speech recognition. This study aims to assess a system that supports aggregation of visual features to audio features during recognition of non-articulatory sounds in noisy environments. Thehe methods Mel-Frequency Cepstrum Coefficients and Laplace transform were used to extract audio features, Convolutional Neural Network to extract video features, and Support Vector Machine to recognize audio and Long Short-Term Memory networks for video recognition. Report experimental results regarding the accuracy, recall and precision of the system on a set of 585 sounds was achieved. Overall, the results indicate that video information can complement audio recognition and assist non-articulatory sound recognition.

/pdf/an-analysis-of-visual-speech-features-for-recognition-of-non-5ujbagh5jp.pdf

An Analysis of Visual Speech Features for Recognition of Non-articulatory Sounds using Machine Learning

Visual lip gestures observed whilst lipreading have a few working definitions, the most common two are; `the visual equivalent of a phoneme' and `phonemes which are indistinguishable on the lips'. To date there is no formal definition, in part because to date we have not established a two-way relationship or mapping between visemes and phonemes. Some evidence suggests that visual speech is highly dependent upon the speaker. So here, we use a phoneme-clustering method to form new phoneme-to-viseme maps for both individual and multiple speakers. We test these phoneme to viseme maps to examine how similarly speakers talk visually and we use signed rank tests to measure the distance between individuals. We conclude that broadly speaking, speakers have the same repertoire of mouth gestures, where they differ is in the use of the gestures.

Comparing heterogeneous visual gestures for measuring the diversity of visual speech signals

Visual speech recognition aims to identify the sequence of phonemes from continuous speech. Unlike the traditional approach of using 2D image feature extraction methods to derive features of each video frame separately, this paper proposes a new approach using a 3D (spatio-temporal) Discrete Cosine Transform to extract features of each feasible sub-sequence of an input video which are subsequently classified individually using Support Vector Machines and combined to find the most likely phoneme sequence using a tailor-made Hidden Markov Model. The algorithm is trained and tested on the VidTimit database to recognise sequences of phonemes as well as visemes (visual speech units). Furthermore, the system is extended with the training on phoneme or viseme pairs (biphones) to counteract the human speech ambiguity of co-articulation. The test set accuracy for the recognition of phoneme sequences is 20%, and the accuracy of viseme sequences is 39%. Both results improve the best values reported in other papers by approximately 2%. The contribution of the result is three-fold: Firstly, this paper is the first to show that 3D feature extraction methods can be applied to continuous sequence recognition tasks despite the unknown start positions and durations of each phoneme. Secondly, the result confirms that 3D feature extraction methods improve the accuracy compared to 2D features extraction methods. Thirdly, the paper is the first to specifically compare an otherwise identical method with and without using biphones, verifying that the usage of biphones has a positive impact on the result.

Toni Heidenreich

Papers

A three-dimensional approach to Visual Speech Recognition using Discrete Cosine Transforms.