Segmentation and Alignment of Speech and Sketching in a Design Environment

Sketches are commonly used in the early stages of design. Our previous system allows users to sketch mechanical systems that the computer interprets. However, some parts of the mechanical system might be too hard or too complicated to express in the sketch. Adding speech recognition to create a multimodal system would move us toward our goal of creating a more natural user interface. This thesis examines the relationship between the verbal and sketch input, particularly how to segment and align the two inputs. Toward this end, subjects were recorded while they sketched and talked. These recordings were transcribed, and a set of rules to perform segmentation and alignment was created. These rules represent the knowledge that the computer needs to perform segmentation and alignment. The rules successfully interpreted the 24 data sets that they were given.

Visual Speech Synthesis by Morphing Visemes

We present MikeTalk, a text-to-audiovisual speech synthesizer which converts input text into an audiovisual speech stream. MikeTalk is built using visemes, which are a small set of images spanning a large range of mouth shapes. The visemes are acquired from a recorded visual corpus of a human subject which is specifically designed to elicit one instantiation of each viseme. Using optical flow methods, correspondence from every viseme to every other viseme is computed automatically. By morphing along this correspondence, a smooth transition between viseme images may be generated. A complete visual utterance is constructed by concatenating viseme transitions. Finally, phoneme and timing information extracted from a text-to-speech synthesizer is exploited to determine which viseme transitions to use, and the rate at which the morphing process should occur. In this manner, we are able to synchronize the visual speech stream with the audio speech stream, and hence give the impression of a photorealistic talking face.

Perceptual Evaluation of Video-Realistic Speech

abstract With many visual speech animation techniques now available, there is a clear need for systematic perceptual evaluation schemes. We describe here our scheme and its application to a new video-realistic (potentially indistinguishable from real recorded video) visual-speech animation system, called Mary 101. Two types of experiments were performed: a) distinguishing visually between real and synthetic image- sequences of the same utterances, ("Turing tests") and b) gauging visual speech recognition by comparing lip-reading performance of the real and synthetic image-sequences of the same utterances ("Intelligibility tests"). Subjects that were presented randomly with either real or synthetic image-sequences could not tell the synthetic from the real sequences above chance level. The same subjects when asked to lip-read the utterances from the same image-sequences recognized speech from real image-sequences significantly better than from synthetic ones. However, performance for both, real and synthetic, were at levels suggested in the literature on lip-reading. We conclude from the two experiments that the animation of Mary 101 is adequate for providing a percept of a talking head. However, additional effort is required to improve the animation for lip-reading purposes like rehabilitation and language learning. In addition, these two tasks could be considered as explicit and implicit perceptual discrimination tasks. In the explicit task (a), each stimulus is classified directly as a synthetic or real image-sequence by detecting a possible difference between the synthetic and the real image-sequences. The implicit perceptual discrimination task (b) consists of a comparison between visual recognition of speech of real and synthetic image-sequences. Our results suggest that implicit perceptual discrimination is a more sensitive method for discrimination between synthetic and real image-sequences than explicit perceptual discrimination.

Performance of postlinguistically deaf cochlear implant patients on the connected speech test (version 3)

This paper discusses a study on postlingual cochlear implantees and the effectiveness of the CST in evaluating enhancement of speech recognition abilities.

Evaluation of multiple speech processing combinations in the Cochlear Nucleus 5 cochlear implant system using R-Space simulation

Difficulty understanding speech in the presence of background noise is a common report among cochlear implant recipients. The purpose of this research is to evaluate speech processing options currently available in the Cochlear Nucleus 5 sound processor to determine the best option for improving speech recognition in noise.

Assessment of PD Speech Anomalies @ Home

Background: Voice processing in real-time is challenging. A drawback of previous work for Hypokinetic Dysarthria (HKD) recognition is the requirement of controlled settings in a laboratory environment. A personal digital assistant (PDA) has been developed for home assessment of PD patients. The PDA offers sound processing capabilities, which allow for developing a module for recognition and quantification HKD. Objective: To compose an algorithm for assessment of PD speech severity in the home environment based on a review synthesis. Methods: A two-tier review methodology is utilized. The first tier focuses on real-time problems in speech detection. In the second tier, acoustics features that are robust to medication changes in Levodopa-responsive patients are investigated for HKD recognition. Keywords such as Hypokinetic Dysarthria , and Speech recognition in real time were used in the search engines. IEEE explorer produced the most useful search hits as compared to Google Scholar, ELIN, EBRARY, PubMed and LIBRIS. Results: Vowel and consonant formants are the most relevant acoustic parameters to reflect PD medication changes. Since relevant speech segments (consonants and vowels) contains minority of speech energy, intelligibility can be improved by amplifying the voice signal using amplitude compression. Pause detection and peak to average power rate calculations for voice segmentation produce rich voice features in real time. Enhancements in voice segmentation can be done by inducing Zero-Crossing rate (ZCR). Consonants have high ZCR whereas vowels have low ZCR. Wavelet transform is found promising for voice analysis since it quantizes non-stationary voice signals over time-series using scale and translation parameters. In this way voice intelligibility in the waveforms can be analyzed in each time frame. Conclusions: This review evaluated HKD recognition algorithms to develop a tool for PD speech home-assessment using modern mobile technology. An algorithm that tackles realtime constraints in HKD recognition based on the review synthesis is proposed. We suggest that speech features may be further processed using wavelet transforms and used with a neural network for detection and quantification of speech anomalies related to PD. Based on this model, patients' speech can be automatically categorized according to UPDRS speech ratings.

Evolvable hardware applied to voice recognition

This paper presents some results of the application on Evolvable Hardware (EHW) in the area of voice recognition. Evolvable Hardware is able to change inner connections, using genetic learning techniques, adapting its own functionality to external condition changing. This technique became feasible by the improvement of the Programmable Logic Devices. Nowadays, it is possible to have, in a single device, the ability to change, on-line and in real-time, part of its own circuit. This work proposes a reconfigurable architecture of a system that is able to receive voice commands to execute special tasks as, to help handicapped persons in their daily home routines. The idea is to collect several voice samples, process them through algorithms based on Mel - Ceptrais theory to obtain their numerical coefficients for each sample, which, compose the universe of search used by genetic algorithm. The voice patterns considered, are limited to seven sustained Portuguese vowel phonemes (a, eh, e, i, oh, o, u).

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

Visual Speech Segmentation: Using Facial Cues to Locate Word Boundaries in Continuous Speech

Speech is typically a multimodal phenomenon, yet few studies have focused on the exclusive contributions of visual cues to language acquisition. To address this gap, we investigated whether visual prosodic information can facilitate speech segmentation. Previous research has demonstrated that language learners can use lexical stress and pitch cues to segment speech and that learners can extract this information from talking faces. Thus, we created an artificial speech stream that contained minimal segmentation cues and paired it with two synchronous facial displays in which visual prosody was either informative or uninformative for identifying word boundaries. Across three familiarisation conditions (audio stream alone, facial streams alone, and paired audiovisual), learning occurred only when the facial displays were informative to word boundaries, suggesting that facial cues can help learners solve the early challenges of language acquisition.

The Neural Substrates of Multisensory Speech Perception

Comprehending speech is one of the most important human behaviors, but we are only beginning to understand how the brain accomplishes this difficult task. One key to speech perception seems to be that the brain integrates the independent sources of information available in the auditory and visual modalities in a process known as multisensory integration. This allows speech perception to be accurate, even in environments in which one modality or the other is ambiguous in the context of noise. Previous electrophysiological and functional magnetic resonance imaging (fMRI) experiments have implicated the posterior superior temporal sulcus (STS) in auditory-visual integration of both speech and non-speech stimuli. While evidence from prior imaging studies have found increases in STS activity for audiovisual speech compared with unisensory auditory or visual speech, these studies do not provide a clear mechanism as to how the STS communicates with early sensory areas to integrate the two streams of information into a coherent audiovisual percept. Furthermore, it is currently unknown if the activity within the STS is directly correlated with strength of audiovisual perception. In order to better understand the cortical mechanisms that underlie audiovisual speech perception, we first studied the STS activity and connectivity during the perception of speech with auditory and visual components of varying intelligibility. By studying fMRI activity during these noisy audiovisual speech stimuli, we found that STS connectivity with auditory and visual cortical areas mirrored perception; when the information from one modality is unreliable and noisy, the STS interacts less with the cortex processing that modality and more with the cortex processing the reliable information. We next characterized the role of STS activity during a striking audiovisual speech illusion, the McGurk effect, to determine if activity within the STS predicts how strongly a person integrates auditory and visual speech information. Subjects with greater susceptibility to the McGurk effect exhibited stronger fMRI activation of the STS during perception of McGurk syllables, implying a direct correlation between strength of audiovisual integration of speech and activity within an the multisensory STS.

Speech Intelligibility in Noise With a Pinna Effect Imitating Cochlear Implant Processor.

OBJECTIVE To evaluate the speech intelligibility in noise with a new cochlear implant (CI) processor that uses a pinna effect imitating directional microphone system. STUDY DESIGN Prospective experimental study. SETTING Tertiary referral center. PATIENTS Ten experienced, unilateral CI recipients with bilateral severe-to-profound hearing loss. INTERVENTION All participants performed speech in noise tests with the Opus 2 processor (omnidirectional microphone mode only) and the newer Sonnet processor (omnidirectional and directional microphone mode). MAIN OUTCOME MEASURE The speech reception threshold (SRT) in noise was measured in four spatial settings. The test sentences were always presented from the front. The noise was arriving either from the front (S0N0), the ipsilateral side of the CI (S0NIL), the contralateral side of the CI (S0NCL), or the back (S0N180). RESULTS The directional mode improved the SRTs by 3.6 dB (p < 0.01), 2.2 dB (p < 0.01), and 1.3 dB (p < 0.05) in the S0N180, S0NIL, and S0NCL situations, when compared with the Sonnet in the omnidirectional mode. There was no statistically significant difference in the S0N0 situation. No differences between the Opus 2 and the Sonnet in the omnidirectional mode were observed. CONCLUSION Speech intelligibility with the Sonnet system was statistically different to speech recognition with the Opus 2 system suggesting that CI users might profit from the pinna effect imitating directionality mode in noisy environments.

Automatic Understanding of ATC Speech: Study of Prospectives and Field Experiments for Several Controller Positions

Although there has been a lot of interest in recognizing and understanding air traffic control (ATC) speech, none of the published works have obtained detailed field data results. We have developed a system able to identify the language spoken and recognize and understand sentences in both Spanish and English. We also present field results for several in-tower controller positions. To the best of our knowledge, this is the first time that field ATC speech (not simulated) is captured, processed, and analyzed. The use of stochastic grammars allows variations in the standard phraseology that appear in field data. The robust understanding algorithm developed has 95% concept accuracy from ATC text input. It also allows changes in the presentation order of the concepts and the correction of errors created by the speech recognition engine improving it by 17% and 25%, respectively, absolute in the percentage of fully correctly understood sentences for English and Spanish in relation to the percentages of fully correctly recognized sentences. The analysis of errors due to the spontaneity of the speech and its comparison to read speech is also carried out. A 96% word accuracy for read speech is reduced to 86% word accuracy for field ATC data for Spanish for the "clearances" task confirming that field data is needed to estimate the performance of a system. A literature review and a critical discussion on the possibilities of speech recognition and understanding technology applied to ATC speech are also given.

Improving automatic detection of obstructive sleep apnea through nonlinear analysis of sustained speech

We present a novel approach for the detection of severe obstructive sleep apnea (OSA) based on patients' voices introducing nonlinear measures to describe sustained speech dynamics. Nonlinear features were combined with state-of-the-art speech recognition systems using statistical modeling techniques (Gaussian mixture models, GMMs) over cepstral parameterization (MFCC) for both continuous and sustained speech. Tests were performed on a database including speech records from both severe OSA and control speakers. A 10 % relative reduction in classification error was obtained for sustained speech when combining MFCC-GMM and nonlinear features, and 33 % when fusing nonlinear features with both sustained and continuous MFCC-GMM. Accuracy reached 88.5 % allowing the system to be used in OSA early detection. Tests showed that nonlinear features and MFCCs are lightly correlated on sustained speech, but uncorrelated on continuous speech. Results also suggest the existence of nonlinear effects in OSA patients' voices, which should be found in continuous speech.

Adapting a speech into sign language translation system to a new domain

This paper presents a methodology for adapting an advanced communication system for deaf people in a new domain. This methodology is a user-centered design approach consisting of four main steps: requirement analysis, parallel corpus generation, technology adaptation to the new domain, and finally, system evaluation. In this paper, the new considered domain has been the dialogues in a hotel reception. With this methodology, it was possible to develop the system in a few months, obtaining very good performance: good speech recognition and translation rates (around 90%) with small processing times.

GTH-UPM system for search on speech evaluation

This paper describes the GTH-UPM system for the Albayzin 2014 Search on Speech Evaluation. Teh evaluation task consists of searching a list of terms/queries in audio files. The GTH-UPM system we are presenting is based on a LVCSR (Large Vocabulary Continuous Speech Recognition) system. We have used MAVIR corpus and the Spanish partition of the EPPS (European Parliament Plenary Sessions) database for training both acoustic and language models. The main effort has been focused on lexicon preparation and text selection for the language model construction. The system makes use of different lexicon and language models depending on the task that is performed. For the best configuration of the system on the development set, we have obtained a FOM of 75.27 for the deyword spotting task.