Speechreading aids based on automatic speech recognition: Prospects for the automatic generation of cued speech

Combined speech enhancement and auditory modelling for robust distributed speech recognition

In this paper, the improvements in the recently implemented Kannada speech recognition system is demonstrated in detail. The Kannada automatic speech recognition (ASR) system consists of ASR models which are created by using Kaldi, IVRS call flow and weather and agricultural commodity prices information databases. The task specific speech data used in the recently developed spoken dialogue system had high level of different background noises. The different types of noises present in collected speech data had an adverse effect on the on line and off line speech recognition performances. Therefore, to improve the speech recognition accuracy in Kannada ASR system, a noise reduction algorithm is developed which is a fusion of spectral subtraction with voice activity detection (SS-VAD) and minimum mean square error spectrum power estimator based on zero crossing (MMSE-SPZC) estimator. The noise elimination algorithm is added in the system before the feature extraction part. An alternative ASR models are created using subspace Gaussian mixture models (SGMM) and deep neural network (DNN) modeling techniques. The experimental results show that, the fusion of noise elimination technique and SGMM/DNN based modeling gives a better relative improvement of 7.68% accuracy compared to the recently developed GMM-HMM based ASR system. The least word error rate (WER) acoustic models could be used in spoken dialogue system. The developed spoken query system is tested from Karnataka farmers under uncontrolled environment.

The automatic speech recognition (ASR) system based on deep neural network is easy to be attacked by an adversarial example due to the vulnerability of neural network, which is a hot topic in recent years. The adversarial example does harm to the ASR system, especially if the common-dependent ASR goes wrong, it will lead to serious consequences. To improve the robustness and security of the ASR system, the defense method against adversarial examples must be proposed. Based on this idea, we propose an algorithm of devastation and detection on adversarial examples which can attack the current advanced ASR system. We choose advanced text-dependent and command-dependent ASR system as our target system. Generating adversarial examples by the OPT on text-dependent ASR and the GA-based algorithm on command-dependent ASR. The main idea of our method is input transformation of the adversarial examples. Different random intensities and kinds of noise are added to the adversarial examples to devastate the perturbation previously added to the normal examples. From the experimental results, the method performs well. For the devastation of examples, the original speech similarity before and after adding noise can reach 99.68%, the similarity of the adversarial examples can reach 0%, and the detection rate of the adversarial examples can reach 94%.

Manual transcription of audio databases for the development of automatic speech recognition (ASR) systems is a costly and time-consuming process. In the context of deriving acoustic models adapted to a specific application, or in low-resource scenarios, it is therefore essential to explore alternatives capable of improving speech recognition results. In this paper, we investigate the relevance of foreign data characteristics, in particular domain and language, when using this data as an auxiliary data source for training ASR acoustic models based on deep neural networks (DNNs). The acoustic models are evaluated on a challenging bilingual database within the scope of the MediaParl project. Experimental results suggest that in-language (but out-of-domain) data is more beneficial than in-domain (but out-of-language) data when employed in either supervised or semi-supervised training of DNNs. The best performing ASR system, an HMM/GMM acoustic model that exploits DNN as a discriminatively trained feature extractor outperforms the best performing HMM/DNN hybrid by about 5 % relative (in terms of WER). An accumulated relative gain with respect to the MFCC-HMM/GMM baseline is about 30 % WER.

Some of the speech databases and large spoken language corpora that have been collected during the last fifteen years have been (at least partly) annotated with a broad phonetic transcription. Such phonetic transcriptions are often validated in terms of their resemblance to a handcrafted reference transcription. However, there are at least two methodological issues questioning this validation method. First, no reference transcription can fully represent the phonetic truth. This calls into question the status of such a transcription as a single reference for the quality of other phonetic transcriptions. Second, phonetic transcriptions are often generated to serve various purposes, none of which are considered when the transcriptions are compared to a reference transcription that was not made with the same purpose in mind. Since phonetic transcriptions are often used for the development of automatic speech recognition (ASR) systems, and since the relationship between ASR performance and a transcription’s resemblance to a reference transcription does not seem to be straightforward, we verified whether phonetic transcriptions that are to be used for ASR development can be justifiably validated in terms of their similarity to a purpose-independent reference transcription. To this end, we validated canonical representations and manually verified broad phonetic transcriptions of read speech and spontaneous telephone dialogues in terms of their resemblance to a handcrafted reference transcription on the one hand, and in terms of their suitability for ASR development on the other hand. Whereas the manually verified phonetic transcriptions resembled the reference transcription much closer than the canonical representations, the use of both transcription types yielded similar recognition results. The difference between the outcomes of the two validation methods has two implications. First, ASR developers can save themselves the effort of collecting expensive reference transcriptions in order to validate phonetic transcriptions of speech databases or spoken language corpora. Second, phonetic transcriptions should preferably be validated in terms of the application they will serve because a higher resemblance to a purpose-independent reference transcription is no guarantee for a transcription to be better suited for ASR development.

The method of decoding by Viterbi is used in areas like convolutional codes in digital TV, wireless local area networks, satellite communication, mobile relay. Also, the method is used in the development of Automatic Speech Recognition (ASR) and storage systems that work automatically. For Viterbi decoder-based architectures with low latency and complexity, which proposes error detection techniques that are effective. This paper explores the Viterbi algorithm which has two types of approaches for two types of subparts. Important aspects of any communication system are area/power consumption and throughput /efficiency. Minimization of these aspects is the need for an efficient system. This paper explores unwanted logical block reduction by modifying the present logical block. This paper explores signature-based approaches which result in acceptable efficiency. Also, another approach is used to achieve error detection in permanent and transient faults. This error detection is achieved by recomputing with encoded operands. Encoding means the use of shifting operation or the use of rotation operation. This approach makes the system slightly reliable and efficient.

This paper describes open source software (available at https://github.com/robotology/natural-speech) to build automatic speech recognition (ASR) systems and run them within the YARP platform. The toolkit is designed (i) to allow non-ASR experts to easily create their own ASR system and run it on iCub and (ii) to build deep learning-based models specifically addressing the main challenges an ASR system faces in the context of verbal human–iCub interactions. The toolkit mostly consists of Python, C++ code and shell scripts integrated in YARP. As additional contribution, a second codebase (written in Matlab) is provided for more expert ASR users who want to experiment with bio-inspired and developmental learning-inspired ASR systems. Specifically, we provide code for two distinct kinds of speech recognition: “articulatory” and “unsupervised” speech recognition. The first is largely inspired by influential neurobiological theories of speech perception which assume speech perception to be mediated by brain motor cortex activities. Our articulatory systems have been shown to outperform strong deep learning-based baselines. The second type of recognition systems, the “unsupervised” systems, do not use any supervised information (contrary to most ASR systems, including our articulatory systems). To some extent, they mimic an infant who has to discover the basic speech units of a language by herself. In addition, we provide resources consisting of pre-trained deep learning models for ASR, and a 2.5-h speech dataset of spoken commands, the VoCub dataset, which can be used to adapt an ASR system to the typical acoustic environments in which iCub operates.

In this study, a real-time automatic speech recognition (ASR) system based on the Kaldi ASR toolkit, with low-latency and customizable models, without any internet connection, was developed. The proposed ASR system includes a voice activity detection (VAD) module and an audio transmitter as a front-end speech processing and a decoder for the received audio signals. The ASR system was evaluated in terms of ASR accuracy and speech processing speed. Consequently, the ASR system achieved high ASR accuracy on the CSJ (Corpus of Spontaneous Japanese) test set with super low-latency.

Challenges of Automatic Speech Recognition for medical interviews - research for Polish language

We report insights from translating Spanish conversational telephone speech into English text by cascading an automatic speech recognition (ASR) system with a statistical machine translation (SMT) system. The key new insight is that the informal register of conversational speech is a greater challenge for ASR than for SMT: the BLEU score for translating the reference transcript is 64%, but drops to 32% for translating automatic transcripts, whose word error rate (WER) is 40%. Several strategies are examined to mitigate the impact of ASR errors on the SMT output: (i) providing the ASR lattice, instead of the 1-best output, as input to the SMT system, (ii) training the SMT system on Spanish ASR output paired with English text, instead of Spanish reference transcripts, and (iii) improving the core ASR system. Each leads to consistent and complementary improvements in the SMT output. Compared to translating the 1-best output of an ASR system with 40% WER using an SMT system trained on Spanish reference transcripts, translating the output lattice of a better ASR system with 35% WER using an SMT system trained on ASR output improves BLEU from 32% to 38%.

These days, automatic speech recognition (ASR) systems achieve higher and higher accuracy rates. The score drops significantly, in case when the ASR system is being used with a non-native speaker of the language to be recognized. The main reason is specific pronunciation and accent features. A limited volume of labeled non-native speech datasets makes it difficult to train new ASR systems for non-native speakers.

Great strides have been made in the development of automatic speech recognition (ASR) technology over the past thirty years. Most of this effort has been centered around the extension and improvement of Hidden Markov Model (HMM) approaches to ASR. Current commercially-available and industry systems based on HMMs can perform well for certain situational tasks that restrict variability such as phone dialing or limited voice commands. However, the holy grail of ASR systems is performance comparable to humans—in other words, the ability to automatically transcribe unrestricted conversational speech spoken by an infinite number of speakers under varying acoustic environments. This goal is far from being reached. Key to the success of ASR is effective modeling of variability in the speech signal. This tutorial will review the basics of ASR and the various ways in which our current knowledge of speech production, speech perception and prosody can be exploited to improve robustness at every level of the system.

The purpose of this study was to determine the extent to which automatic speech recognition (ASR) systems and human speech output to ASR systems are affected when users perform complex tasks in a noisy, stressful simulated tank environment. A second objective was to determine whether the type of auditory information input (monaural or spatial) affected user task performance, including the output of speech to ASR systems. Subjects performed simultaneous radio communication and tank driving tasks. Independent variables included auditory display configuration, driving speed, and subject type (soldier or civilian). Dependent variables included 1) the proportion of radio channel changes correctly recognized by the ASR; 2) the proportion and types of speech errors in radio channel changes; 3) the number of accurate responses to the radio messages; and 4) subject ratings of stress and workload. Subjects were six male U.S. Army personnel and six male civilians. Results indicated that ASR and human speech output were not significantly affected by any of the independent variables. A mean of 95.5% of all subject verbal commands was recognized by the ASR system. Spatialized radio messages significantly enhanced the ability of the user to understand speech communications from multiple channels. However, spatial audio information input had no significant effect on user speech output or on ASR performance. In general, ASR and spatial audio displays have potential as technologies of interest in high noise, stressful tank environments in which complex, concurrent tasks are performed.

<sec> <title>BACKGROUND</title> Code-switching between Egyptian Arabic (ARZ) and English is ubiquitous in clinical settings across the Arab world, yet no dedicated benchmark exists for evaluating Automatic Speech Recognition (ASR) systems under these conditions. Existing Arabic ASR benchmarks evaluate models on Modern Standard Arabic or single-dialect speech without medical vocabulary or code-switching. </sec> <sec> <title>OBJECTIVE</title> To introduce the Clinera ASR Benchmark, the first benchmark targeting medical ARZ-EN code-switched speech, and to evaluate commercial and open-source ASR systems on accurate recognition of medical terminology using both standard and novel medical-term-aware metrics </sec> <sec> <title>METHODS</title> We curated 683 utterances of Egyptian Arabic-English medical speech with dense medical-term annotations. We evaluated six ASR systems: the proprietary ElevenLabs Scribe v1, domain-adapted ArAZN-Whisper-S (244M parameters), Whisper-Large-V3, SeamlessM4T v2, Wav2Vec2 Large AR, and Whisper-Medium. We computed standard ASR metrics (WER, CER, MER) and proposed novel medical-term metrics (MT-Precision, MT-Recall, MT-F1, MT-wF1 weighted by inverse document frequency). Statistical comparisons used bootstrap confidence intervals and Wilcoxon signed-rank tests with Bonferroni correction. </sec> <sec> <title>RESULTS</title> ElevenLabs Scribe v1 achieved the lowest WER (27.8%) and highest MT-wF1 (60.5%), outperforming all open models by more than six times its size on medical-term recognition. General-purpose multilingual models achieved higher WER while almost entirely failing to recognize medical terms. Among open models, ArAZN-Whisper-S dominated on medical-term efficiency (26.0 MT-wF1 per 100M parameters). Even the best commercial system produced 11 fatal or high-risk medical errors affecting 1.6% of the corpus. </sec> <sec> <title>CONCLUSIONS</title> Current ASR systems exhibit a critical gap between general transcription accuracy and medical-term recognition in code-switched Arabic-English speech. Our benchmark and novel MT-metrics provide the first standardized evaluation framework for this clinically important setting, revealing that even top-performing systems pose patient safety risks through medical terminology errors. </sec>

Current automatic speech recognition (ASR) systems achieve over 90–95% accuracy, depending on the methodology applied and datasets used. However, the level of accuracy decreases significantly when the same ASR system is used by a non-native speaker of the language to be recognized. At the same time, the volume of labeled datasets of non-native speech samples is extremely limited both in size and in the number of existing languages. This problem makes it difficult to train or build sufficiently accurate ASR systems targeted at non-native speakers, which, consequently, calls for a different approach that would make use of vast amounts of large unlabeled datasets. In this paper, we address this issue by employing dual supervised learning (DSL) and reinforcement learning with policy gradient methodology. We tested DSL in a warm-start approach, with two models trained beforehand, and in a semi warm-start approach with only one of the two models pre-trained. The experiments were conducted on English language pronounced by Japanese and Polish speakers. The results of our experiments show that creating ASR systems with DSL can achieve an accuracy comparable to traditional methods, while simultaneously making use of unlabeled data, which obviously is much cheaper to obtain and comes in larger sizes.