Automatic Speech Recognition Engine Research Articles

An Automatic Speaker Clustering Pipeline for the Air Traffic Communication Domain

In air traffic management (ATM), voice communications are critical for ensuring the safe and efficient operation of aircraft. The pertinent voice communications—air traffic controller (ATCo) and pilot—are usually transmitted in a single channel, which poses a challenge when developing automatic systems for air traffic management. Speaker clustering is one of the challenges when applying speech processing algorithms to identify and group the same speaker among different speakers. We propose a pipeline that deploys (i) speech activity detection (SAD) to identify speech segments, (ii) an automatic speech recognition system to generate the text for audio segments, (iii) text-based speaker role classification to detect the role of the speaker—ATCo or pilot in our case—and (iv) unsupervised speaker clustering to create a cluster of each individual pilot speaker from the obtained speech utterances. The speech segments obtained by SAD are input into an automatic speech recognition (ASR) engine to generate the automatic English transcripts. The speaker role classification system takes the transcript as input and uses it to determine whether the speech was from the ATCo or the pilot. As the main goal of this project is to group the speakers in pilot communication, only pilot data acquired from the classification system is employed. We present a method for separating the speech parts of pilots into different clusters based on the speaker’s voice using agglomerative hierarchical clustering (AHC). The performance of the speaker role classification and speaker clustering is evaluated on two publicly available datasets: the ATCO2 corpus and the Linguistic Data Consortium Air Traffic Control Corpus (LDC-ATCC). Since the pilots’ real identities are unknown, the ground truth is generated based on logical hypotheses regarding the creation of each dataset, timing information, and the information extracted from associated callsigns. In the case of speaker clustering, the proposed algorithm achieves an accuracy of 70% on the LDC-ATCC dataset and 50% on the more noisy ATCO2 dataset.

Explainable Alzheimer’s Disease Detection Using Linguistic Features from Automatic Speech Recognition

Introduction: Alzheimer’s disease (AD) is the most prevalent type of dementia and can cause abnormal cognitive function and progressive loss of essential life skills. Early screening is thus necessary for the prevention and intervention of AD. Speech dysfunction is an early onset symptom of AD patients. Recent studies have demonstrated the promise of automated acoustic assessment using acoustic or linguistic features extracted from speech. However, most previous studies have relied on manual transcription of text to extract linguistic features, which weakens the efficiency of automated assessment. The present study thus investigates the effectiveness of automatic speech recognition (ASR) in building an end-to-end automated speech analysis model for AD detection. Methods: We implemented three publicly available ASR engines and compared the classification performance using the ADReSS-IS2020 dataset. Besides, the SHapley Additive exPlanations algorithm was then used to identify critical features that contributed most to model performance. Results: Three automatic transcription tools obtained mean word error rate texts of 32%, 43%, and 40%, respectively. These automated texts achieved similar or even better results than manual texts in model performance for detecting dementia, achieving classification accuracies of 89.58%, 83.33%, and 81.25%, respectively. Conclusion: Our best model, using ensemble learning, is comparable to the state-of-the-art manual transcription-based methods, suggesting the possibility of an end-to-end medical assistance system for AD detection with ASR engines. Moreover, the critical linguistic features might provide insight into further studies on the mechanism of AD.

Editing machine-generated subtitle templates: A situated subtitler training experience

Automation technologies have altered media localisation workflows as much as practitioners’ workstations and habits. Subtitling systems and streaming services now often integrate built-in automatic speech recognition (ASR) engines, sometimes even combined with machine translation engines, to produce subtitles from audio tracks. The rise of post-editors in the audiovisual translation (AVT) sector, specifically subtitling, has been a reality for some time, thus triggering the need for up-to-date training methods and academic curricula. This article examines the uses and applications of editing practices for machine-generated timed transcriptions in subtitler training environments. A situated learning experience was designed for an international team of eight AVT trainees and three educators to edit raw machine-generated subtitles (both inter- and intra-lingually) for educational videos. The publication of an accessible video book by a publishing house was the ultimate objective of this project, undertaken by an international team of English- and Spanish-speaking postgraduate students and graduates. The feedback collated after this experience through an online questionnaire proved paramount to understanding the use of subtitle post-editing for ASR-produced templates in AVT education. Interestingly, most respondents believed that subtitle post-editing training, be it intralingual or interlingual, should be further embedded in translation curricula while also identifying bottlenecks that AVT educators may find useful when developing activities of this nature.

Real-time Context-Aware Multimodal Network for Activity and Activity-Stage Recognition from Team Communication in Dynamic Clinical Settings.

In clinical settings, most automatic recognition systems use visual or sensory data to recognize activities. These systems cannot recognize activities that rely on verbal assessment, lack visual cues, or do not use medical devices. We examined speech-based activity and activity-stage recognition in a clinical domain, making the following contributions. (1) We collected a high-quality dataset representing common activities and activity stages during actual trauma resuscitation events-the initial evaluation and treatment of critically injured patients. (2) We introduced a novel multimodal network based on audio signal and a set of keywords that does not require a high-performing automatic speech recognition (ASR) engine. (3) We designed novel contextual modules to capture dynamic dependencies in team conversations about activities and stages during a complex workflow. (4) We introduced a data augmentation method, which simulates team communication by combining selected utterances and their audio clips, and showed that this method contributed to performance improvement in our data-limited scenario. In offline experiments, our proposed context-aware multimodal model achieved F1-scores of 73.2±0.8% and 78.1±1.1% for activity and activity-stage recognition, respectively. In online experiments, the performance declined about 10% for both recognition types when using utterance-level segmentation of the ASR output. The performance declined about 15% when we omitted the utterance-level segmentation. Our experiments showed the feasibility of speech-based activity and activity-stage recognition during dynamic clinical events.

"Mm-hm," "Uh-uh": are non-lexical conversational sounds deal breakers for the ambient clinical documentation technology?

Ambient clinical documentation technology uses automatic speech recognition (ASR) and natural language processing (NLP) to turn patient-clinician conversations into clinical documentation. It is a promising approach to reducing clinician burden and improving documentation quality. However, the performance of current-generation ASR remains inadequately validated. In this study, we investigated the impact of non-lexical conversational sounds (NLCS) on ASR performance. NLCS, such as Mm-hm and Uh-uh, are commonly used to convey important information in clinical conversations, for example, Mm-hm as a "yes" response from the patient to the clinician question "are you allergic to antibiotics?" In this study, we evaluated 2 contemporary ASR engines, Google Speech-to-Text Clinical Conversation ("Google ASR"), and Amazon Transcribe Medical ("Amazon ASR"), both of which have their language models specifically tailored to clinical conversations. The empirical data used were from 36 primary care encounters. We conducted a series of quantitative and qualitative analyses to examine the word error rate (WER) and the potential impact of misrecognized NLCS on the quality of clinical documentation. Out of a total of 135647 spoken words contained in the evaluation data, 3284 (2.4%) were NLCS. Among these NLCS, 76 (0.06% of total words, 2.3% of all NLCS) were used to convey clinically relevant information. The overall WER, of all spoken words, was 11.8% for Google ASR and 12.8% for Amazon ASR. However, both ASR engines demonstrated poor performance in recognizing NLCS: the WERs across frequently used NLCS were 40.8% (Google) and 57.2% (Amazon), respectively; and among the NLCS that conveyed clinically relevant information, 94.7% and 98.7%, respectively. Current ASR solutions are not capable of properly recognizing NLCS, particularly those that convey clinically relevant information. Although the volume of NLCS in our evaluation data was very small (2.4% of the total corpus; and for NLCS that conveyed clinically relevant information: 0.06%), incorrect recognition of them could result in inaccuracies in clinical documentation and introduce new patient safety risks.

Consensus Automatic Speech Recognition (CASR) in Cognitive Testing

AbstractBackgroundScoring verbal cognitive tests with automatic speech recognition (ASR) engines increases the efficiency of scoring and provides word timestamps that enable detailed temporal analyses of spoken responses. Here, we describe consensus ASR (CASR) procedures that incorporate multiple ASR engines to increase transcription and timing accuracy and generate CASR transcript confidence scores.MethodSeven ASR engines produced automatic transcriptions of both speech database samples (GMU Speech Accent Archive and NUS Auditory English Lexicon Project) and verbal test responses of 41 subjects from the California Cognitive Assessment Battery (CCAB). A novel Recognizer Output Voting Error Reduction (ROVER) algorithm was used to mutually align the transcripts, and a Bayesian weighted voting algorithm produced the best CASR transcript, mean word timestamps, and consensus scores. Word error rates (WER) gauged CASR accuracy against either predetermined or manually corrected transcripts.ResultDatabase sentence WERs from 1767 subjects ranged from a mean of 22% (Windows10 UWP) to 6% (Rev.ai) with CASR producing 5%, with no significant gender or age effects but better performance for native english speakers (Figure 1). In CCAB test responses, for limited word response tests CASR WERs ranged from 3% to less than 1% (Figure 2); for expansive word response tests CASR WERs ranged from 8% to 2% (Figure 3); and for discursive speech, CASR WERs ranged from 6% to 5%. Word start time ASR estimates for 594 database words in lists ranged in mean deviations from true times from 250ms std.dev. (Google) to 17ms std.dev. (Amazon) with CASR obtaining 14ms errors (Figure 4). Finally, consensus confidence scores from CCAB test responses, ranging from 0 to 1 (1 = complete agreement across ASR engines), show that CASR words with consensus scores above 0.8 and 0.9 are correct >99% and >99.8% of the time, respectively (Figure 5).ConclusionCASR produces transcripts for verbal test responses accurate enough for estimating scores in most limited word response tests. In large vocabulary response tests, CASR transcripts facilitate quick manual correction, and confidence values can identify transcript words needing manual correction. Patterns in CASR errors also indicate future substantial reductions to CASR WER on a per test basis.

Consensus automatic speech recognition (CASR) in the California Cognitive Assessment Battery (CCAB).

Recent reports have investigated the use of automatic speech recognition (ASR) to analyze and score verbal responses in cognitive tests. ASR scoring is objective, permits the efficient computerized administration of verbal tests, and generates timestamps that enable the detailed temporal analysis of responses. However, ASR transcription accuracy varies by engine, task, and participant, and ASR can incorrectly score responses from participants with atypical speech patterns. Here we describe the speech-transcription pipeline of the California Cognitive Assessment Battery (CCAB), which incorporates consensus ASR (CASR) to produce more accurate transcripts than possible with any single ASR engine. We also developed a Transcript Review Tool (TRT) which facilitates the manual correction of mis-transcribed words in problem subjects. Figure 1 shows the CCAB speech transcription pipeline. Realtime ASR transcriptions are obtained along with the transcriptions of the digital recordings of responses using six cloud-based ASR engines (e.g., Google, etc.). Individual transcripts are then combined to produce a "consensus" transcript, and a transcription confidence measure based primarily on the agreement between ASR engines (Figure 2). If needed, "consensus" transcripts can be manually corrected using the Transcript Review Tool which enables the review of all words or just those words below a predefined CASR confidence threshold (Figure 3). ASR transcriptions were obtained from 442 healthy adults (mean age = 65.1 ±14.4) who each underwent three days of cognitive testing that included 25 verbal tests. In all, approximately 276 hours of speech were transcribed. Preliminary analyses show that CASR transcription accuracy surpassed 99% for tests with limited response sets (e.g., digit span, verbal list learning, face-name binding, etc.) and exceeded 95% for discursive speech tests (e.g., picture description and logical memory). CASR transcription is more accurate than that of any single ASR engine. When combined with the TRT, "consensus" ASR can produce error-free, timestamped transcripts that enable the detailed analysis of verbal responses from older individuals at risk of cognitive decline.

Analyzing field audio of parent-child book reading activities across various audio capture devices

Language ENvironment Analysis (LENA) is a light weight audio capture device commonly used to monitor language including frequency of parent-child interactions for research purposes. However, various factors including price and technical limitations often limit the use of LENA for low-income families. Using a smartphone can be a feasible alternative when LENA is not available to practitioners/families. Over the past three decades, significant advancements have resulted in smartphone platforms/microphones/technology, allowing for high quality recorded audio which are available in most households. In this study we compare audio quality and measure performance of several Automatic Speech recognition (ASR) engines on audio captured from iPhone and Android relative to LENA devices. Families who consented in this study recorded reading activities with their children at home using both personal smartphones and LENA. Some challenges we found include recording synchronization, unnecessary background noises, and uneven room acoustics. Audio quality comparison is measured using Speech-Signal-to-noise ratio (SSNR) metric. Both open-source and fine-tuned ASR models are explored, with results reported using overall Word Error Rate (WER), as well as separated by speaker–Child versus Adult. Results show that smartphone platforms can be used versus LENA for child-adult language assessment. [Work sponsored by NSF through Grant Nos. 1918032 and 1918012.]

Speech Enhancement for Robust Speech Recognition Using Weighted Low Rank and Sparse Decomposition Models under Low SNR Conditions

Noise estimation is a crucial stage in speech enhancement (SE), and it commonly necessitates the use of prior models for speech, noise, or both. Prior models, on the other hand, can be ineffective in dealing with unseen nonstationary noise, especially at low signal to noise (SNR) levels. This paper proposes to assess the efficacy of an unsupervised SE approach based on weighted low rank and sparse matrix factorization to estimate noise and speech when neither is available beforehand by decomposing the input noisy spectrum into a low-rank noise component and a sparse speech component. Due to the approximation of the actual rank of noise, these techniques are constrained, and they do not directly exploit the low-rank property in optimization. Nuclear norm minimization (NNM) is the most well-known approach, as it can precisely recover the matrix's rank under certain restricted and theoretical guarantee conditions. NNM, on the other hand, is unable to reliably estimate the matrix rank in many situations. Significant advancements in computer vision and machine learning applications have demonstrated that a weighted nuclear norm minimization (WNNM), overcomes NNM shortcomings, and achieves a superior matrix rank approximation than NNM. Consequently, in this study, we present alternate SE algorithms that make use of weighted low rank and sparsity constraints to separate speech and noise spectrograms. Following that, they were trained and evaluated on a standard Automatic Speech Recognition (ASR) engine to lower the Word Error Rate (WER). Extensive investigations on the impact of real-world noise on speech signals show that the proposed model outperforms the existing state of art models in terms of objective measures like SDR, PESQ, SIG, BAK, OVL, and STOI values in varied noise circumstances under low SNR environments.

QVR: Quranic Verses Recitation Recognition System using PocketSphinx

The recitation of Quran verses according to the actual tajweed is obligatory and it must be accurate and precise in pronunciation. Hence, it should always be reviewed by an expert on the recitation of the Quran. Through the latest technology, this recitation review can be implemented through an application system and it is most appropriate in this current Covid-19 pandemic situation where system application online is deemed to be developed. In this empirical study, a recognition system so-called the Quranic Verse Recitation Recognition (QVR) system using PocketSphinx to convert the Quranic verse from Arabic sound to Roman text and determine the accuracy of reciters, has been developed. The Graphical User Interface (GUI) of the system with a user-friendly environment was designed using Microsoft Visual Basic 6 in an Ubuntu platform. A verse of surah al-Ikhlas has been chosen in this study and the data were collected by recording 855 audios as training data recorded by professional reciters. Another 105 audios were collected as testing data, to test the accuracy of the system. The results indicate that the system obtained a 100% accuracy with a 0.00% of word error rate (WER) for both training and testing data of the said audios via Quran Roman text. The system with automatic speech recognition (ASR) engine system demonstrates that it has been successfully designed and developed, and is significant to be extended further. Added, it will be improved with the addition of other Quran surahs.

A cross-language study of speech recognition systems for English, German, and Hebrew

Despite the growing importance of Automatic Speech Recognition (ASR), its application is still challenging, limited, language-dependent, and requires considerable resources. The resources required for ASR are not only technical, they also need to reflect technological trends and cultural diversity. The purpose of this research is to explore ASR performance gaps by a comparative study of American English, German, and Hebrew. Apart from different languages, we also investigate different speaking styles – utterances from spontaneous dialogues and utterances from frontal lectures (TED-like genre). The analysis includes a comparison of the performance of four ASR engines (Google Cloud, Google Search, IBM Watson, and WIT.ai) using four commonly used metrics: Word Error Rate (WER); Character Error Rate (CER); Word Information Lost (WIL); and Match Error Rate (MER). As expected, findings suggest that English ASR systems provide the best results. Contrary to our hypothesis regarding ASR’s low performance for under-resourced languages, we found that the Hebrew and German ASR systems have similar performance. Overall, our findings suggest that ASR performance is language-dependent and system-dependent. Furthermore, ASR may be genre-sensitive, as our results showed for German. This research contributes a valuable insight for improving ubiquitous global consumption and management of knowledge and calls for corporate social responsibility of commercial companies, to develop ASR under Fair, Reasonable, and Non-Discriminatory (FRAND) terms

Spoken Turkish in television news and debates: Some acoustic and morphological aspects relevant to respeaking

This paper presents a qualitative analysis of spoken Turkish based on approximately 77 minutes of transcribed content from television news and debates with special focus on acoustic and morphological aspects relevant to respeaking, where an edited form of the original verbal content is dictated to a speaker-dependent automatic speech recognition (ASR) engine, whose output is further edited for broadcast-quality subtitles. The data suggest that respeaking can solve only some of the potential problems unscripted speech presents for ASR. On the acoustic level, a respeaker can overcome segmental and suprasegmental variation as well as degraded acoustic conditions, and can partially resolve overlapping speech. On the morphological level, disfluency and deviant morphology can be handled. When paraphrasing the text and dictating punctuation marks under time pressure, a respeaker can hardly control her own pronunciation; deletion, reduced morphemes, etc., might lead to misrecognition. As standard orthography, capitalization, and punctuation are required in subtitles, named entities, figures, morphophonemics and use of apostrophe will require satisfactory solutions during ASR and/or post-editing.

Syllable-Based Indonesian Automatic Speech Recognition

The syllable-based automatic speech recognition (ASR) systems commonly perform better than the phoneme-based ones. This paper focuses on developing an Indonesian monosyllable-based ASR (MSASR) system using an ASR engine called SPRAAK and comparing it to a phoneme-based one. The Mozilla DeepSpeech-based end-to-end ASR (MDSE2EASR), one of the state-of-the-art models based on character (similar to the phoneme-based model), is also investigated to confirm the result. Besides, a novel Kaituoxu SpeechTransformer (KST) E2EASR is also examined. Testing on the Indonesian speech corpus of 5,439 words shows that the proposed MSASR produces much higher word accuracy (76.57%) than the monophone-based one (63.36%). Its performance is comparable to the character-based MDS-E2EASR, which produces 76.90%, and the character-based KST-E2EASR (78.00%). In the future, this monosyllable-based ASR is possible to be improved to the bisyllable-based one to give higher word accuracy. Nevertheless, extensive bisyllable acoustic models must be handled using an advanced method.

V-Speech

Smart glasses are often used in noisy public spaces or industrial settings. Voice commands and automatic speech recognition (ASR) are good user interfaces for such a form factor, but the background noise and interfering speakers pose important challenges. Typical signal processing techniques have limitations in performance and/or hardware resources. V-Speech is a novel solution that captures the voice signal with a vibration sensor located in the nasal pads of smart glasses. Although signal-to-noise ratio (SNR) is much higher with vibration sensor capture, it introduces a "nasal distortion," which must be dealt with. The second part of our proposed solution involves a voice transformation of the vibration signal using a neural network to produce an output that mimics the characteristics of a conventional microphone. We evaluated V-Speech in noise-free and very noisy conditions with 30 volunteer speakers uttering 145 phrases each, and validated its performance on ASR engines, with assessments of voice quality using the Perceptual Evaluation of Speech Quality (PESQ) metric, and with subjective listeners to determine intelligibility, naturalness and overall quality. The results show, in extreme noise conditions, a mean improvement of 50% for Word Error Rate (WER), 1.0 on a scale of 5.0 for PESQ, and speech regarded intelligible, with naturalness rated as fair to good. The output of V-Speech has low noise, sounds natural, and enables clear voice communication in challenging environments.

Improved Speech Command Classification System for Sinhala Language based on Automatic Speech Recognition

The recent advancements in conversational Artificial Intelligence (AI) are fastly getting integrated with every realm of human lives. Conversational agents who can learn, understand human languages and mimic the human thinking process have already created a revolution in human lifestyle. Understanding the intention of a speaker from his natural speech is a significant step in conversational AI. A major challenge that hinders the efficacy of this process is the lack of language resources. In this research, we address this issue and develop a domain-specific speech command classification system for the Sinhala language, one of the low-resourced languages. An effective speech command classification system can be utilized in several value added applications such as speech dialog systems. Our speech command classification system is developed by integrating Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU). The ASR engine is implemented using Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) and it converts a Sinhala speech command into a corresponding text representation. The text classifier, which is implemented as an ensemble unit of several classifiers, predicts the intent of the speaker when provided with the above text output. In this paper, we discuss and evaluate various algorithms and techniques that can be utilized to optimize the performance of both the ASR and text classifier. As well, we present our novel Sinhala speech data corpus of 4.15[Formula: see text]h which is based on the banking domain. As the final outcome, our system reports its Sinhala speech command classification accuracy as 91.03%. It shows that our system outperforms the state-of-the-art speech-to-intent mapping systems developed for the Sinhala language. The individual evaluation on the ASR system reports a 9.91% Word Error Rate and a 19.95% Sentence Error Rate, suggesting the applicability of advanced speech recognition techniques despite the limited language resources. Finally, our findings deliver useful insights on further research in speech command classification in the low-resourced context.

Far-Field Automatic Speech Recognition

The machine recognition of speech spoken at a distance from the microphones, known as far-field automatic speech recognition (ASR), has received a significant increase in attention in science and industry, which caused or was caused by an equally significant improvement in recognition accuracy. Meanwhile, it has entered the consumer market with digital home assistants with a spoken language interface being its most prominent application. Speech recorded at a distance is affected by various acoustic distortions, and consequently, quite different processing pipelines have emerged compared with ASR for close-talk speech. A signal enhancement front end for dereverberation, source separation, and acoustic beamforming is employed to clean up the speech, and the back-end ASR engine is robustified by multicondition training and adaptation. We will also describe the so-called end-to-end approach to ASR, which is a new promising architecture that has recently been extended to the far-field scenario. This tutorial article gives an account of the algorithms used to enable accurate speech recognition from a distance, and it will be seen that, although deep learning has a significant share in the technological breakthroughs, a clever combination with traditional signal processing can lead to surprisingly effective solutions.

Speech Enhancement Parameter Adjustment to Maximize Accuracy of Automatic Speech Recognition

Consumer electronics equipped with a microphone array, such as car navigation devices and headsets commonly implement speech enhancement techniques based on the gradient method to cope with additive noise. However, while these techniques had been originally developed for voice communication and can maximize the signal-to-distortion ratio (SDR), they cannot always maximize automatic speech recognition (ASR) accuracy. For this reason, the front-end speech enhancement parameters have been adjusted by human experts to each environment and acoustic model. In this study, we developed a novel system for maximizing the accuracy of a given ASR engine by automatically adjusting the front-end speech enhancement. The proposed method allows consumers to use ASR through the consumer electronics with less stress when ambient noise varies. A genetic algorithm (GA) is used to generate parameter values of the front-end speech enhancement for particular environments. The generated values can be dynamically assigned to input speech signals by preliminarily clustering the environments based on noise features. In evaluations, parameter values determined by our method outperformed one adjusted by a human expert.

V-Speech

Smart glasses are often used in public environments or industrial scenarios that are relatively noisy. Background noise and sound from competing speakers deteriorate voice communication or performance of automatic speech recognition (ASR). Typically, signal processing techniques are used to reduce noise and enhance voice quality, but they have limitations in performance, hardware and/or computing resources. Voice capturing techniques using bone conducting on the head have been proposed in some experimental and commercial devices, with good robustness against environmental noise, but limited by signal distortions inherent to the capturing method. We present V-Speech, a novel sensing and signal processing solution that enables speech recognition and human-to-human communication in very noisy environments. It captures the voice signal with a vibration sensor located in the nasal pads of smart glasses and performs a transformation to the sensor signal in order to mimic that of a regular microphone in low noise conditions. The signal transformation is key, as it eliminates the "nasal distortion" that is introduced for nasal phonemes in the speech induced vibrations of the nasal bone. The output of V-Speech has low noise, sounds natural, and can be used in voice communication or as input to an off-the-shelf ASR service. We evaluated V-Speech in noise-free and noisy conditions with 30 volunteer speakers uttering 145 phrases and validated its performance on ASR engines and with assessments of voice quality using the Perceptual Evaluation of Speech Quality (PESQ) metric. The results show in extreme noise conditions a mean improvement of 50% for Word Error Rate (WER), and 1.0 on a scale of 5.0 for PESQ. In addition, real life recordings were made under various representative noise conditions, some with sound pressure levels of 93 dBA, which require hearing protection. Subjective listening tests were conducted according to a modified ITU P.835 approach to determine intelligibility, naturalness and overall quality. Under these extreme conditions, where V-Speech achieved 30 dB SNR, subjective results show the speech is intelligible, and the naturalness of the speech is rated as fair to good. This enables clear voice communication in challenging work environments, for example in places with industrial, factory, mining and construction noise. With our proposed smart switching technique between a regular microphone signal and V-Speech, the optimal quality can be maintained from low to high noise conditions.

The suitability of cloud-based speech recognition engines for language learning

As online automatic speech recognition (ASR) engines become more accurate and more widely implemented with CALL software, it becomes important to evaluate the effectiveness and the accuracy of these recognition engines using authentic speech samples. This study investigates two of the most prominent cloud-based speech recognition engines- Apple’s Siri and Google Speech Recognition (GSR) to determine which engine would be more accurate at transcribing L2 learners’ speech. The average recognition accuracy of Siri and GSR is reported using language samples of Japanese learners speaking English. The study also presents a series of computerized speech assessment tasks that were developed by the researchers using a cloud-based speech recognition engine in conjunction with Moodle, a widely used course management system.

A QUIZZING SYSTEM FOR BLIND AND VISUALLY IMPAIRED CANDIDATES

Abstract A major obstacle confronting blind and visually impaired students in their education is the lack of ability to function independently when it comes to certain things like taking exams. This paper is about a voice-enabled quizzing system which will be used to assess the students of a university especially the blind or visually impaired. The system was built on top of the voice over IP (VoIP) technologies in conjunction with an Automatic Speech Recognition (ASR) engine used to transform a speech to its actual text format. Multiple Choice and True/False Question are the only types of question allowed for a quiz; and the interactions with the system are fully operated by voice commands by using a mobile phone, a SIP-enabled device or a SIP-based application to call a number associated to an Interactive Voice Response (IVR) provided with a Voice User Interface (VUI) to manage quizzes as a lecturer and to take quizzes as a student. After the completion of a quiz, the result is provided automatically to the student by audio and email. Immediately after the end date and time set for a quiz is elapsed, an email containing statistical data and the attendants’ results is sent to the lecturer to analyze the performance of the students. However, the lecturer can review the quizzes results anytime by using the Voice User Interface. INTRODUCTION