Wyniki wyszukiwania - BazTech

1

A Study on the Impact of Lombard Effect on Recognition of Hindi Syllabic Units Using CNN Based Multimodal ASR Systems

Uma Maheswari Sadasivam, Shahina A., Rishickesh Ramesh, Nayeemulla Khan A.

Archives of Acoustics

|

2020

|

Vol. 45, No. 3

419--431

EN

Research work on the design of robust multimodal speech recognition systems making use of acoustic, and visual cues, extracted using the relatively noise robust alternate speech sensors is gaining interest in recent times among the speech processing research fraternity. The primary objective of this work is to study the exclusive influence of Lombard effect on the automatic recognition of the confusable syllabic consonant-vowel units of Hindi language, as a step towards building robust multimodal ASR systems in adverse environments in the context of Indian languages which are syllabic in nature. The dataset for this work comprises the confusable 145 consonant-vowel (CV) syllabic units of Hindi language recorded simultaneously using three modalities that capture the acoustic and visual speech cues, namely normal acoustic microphone (NM), throat microphone (TM) and a camera that captures the associated lip movements. The Lombard effect is induced by feeding crowd noise into the speaker’s headphone while recording. Convolutional Neural Network (CNN) models are built to categorise the CV units based on their place of articulation (POA), manner of articulation (MOA), and vowels (under clean and Lombard conditions). For validation purpose, corresponding Hidden Markov Models (HMM) are also built and tested. Unimodal Automatic Speech Recognition (ASR) systems built using each of the three speech cues from Lombard speech show a loss in recognition of MOA and vowels while POA gets a boost in all the systems due to Lombard effect. Combining the three complimentary speech cues to build bimodal and trimodal ASR systems shows that the recognition loss due to Lombard effect for MOA and vowels reduces compared to the unimodal systems, while the POA recognition is still better due to Lombard effect. A bimodal system is proposed using only alternate acoustic and visual cues which gives a better discrimination of the place and manner of articulation than even standard ASR system. Among the multimodal ASR systems studied, the proposed trimodal system based on Lombard speech gives the best recognition accuracy of 98%, 95%, and 76% for the vowels, MOA and POA, respectively, with an average improvement of 36% over the unimodal ASR systems and 9% improvement over the bimodal ASR systems.

2

Method of audio-visual polish speech recognition with use hidden Markov Models

Kubanek M.

Computing, Multimedia and Intelligent Techniques

|

2007

|

Vol. 3, nr 1

87-99

EN

This document contains the novel approach that use other orthogonal sources of information to the acoustic input that not only considerably improve the performance in severely degraded conditions, but also are independent to the type of noise and reverberation. Visual speech is one such source not perturbed by the acoustic environment and noise. It was proposed own approach to lip-tracking for audio-visual speech recognition system and novel audio-visual fusion technique. It was presented video analysis of visual speech for extraction visual features from a talking person in color video sequences. I was developed a method for automatically face, eyes, region of lips, region of corners and detection of contour of lips. Finally, the paper will show results of audio -visual speech recognition in noisy environments.

3

Technique of video features extraction for audio-video speech recognition system

Kubanek M.

Computing, Multimedia and Intelligent Techniques

|

2005

|

Vol. 1 nr 1

181-190

EN

Mainstream automatic speech recognition has focused almost exclusively on the acoustic signal. The performance of these systems degrades considerably in the real word in the presence of noise. It was needed novel approaches that use other orthogonal sources of information to the acoustic input that not only considerably improve the performance in severely degraded conditions, but also are independent to the type of noise and reverberation. Visual speech is one such source not perturbed by the acoustic environment and noise. In this paper, it was presented own approach to lip-tracking for audio-visual speech recognition system. It was presented video analysis of visual speech for extraction visual features from a talking person in color video sequences. It was developed a method for automatically face, eyes, lip's region, lip's corners and lip's contour de-tection. Finally, the paper will show results of lip-tracking depending on various factors (lighting, beard).