Low-Latency Lightweight Streaming Speech Recognition with 8-Bit Quantized Simple Gated Convolutional Neural Networks

Reverberation negatively impacts the performance of automatic speech recognition (ASR). Prior work on quantifying the effect of reverberation has shown that clarity (C50), a parameter that can be estimated from the acoustic impulse response, is correlated with ASR performance. In this paper we propose predicting ASR performance in terms of the word error rate (WER) directly from acoustic parameters via a polynomial, sigmoidal, or neural network fit, as well as blindly from reverberant speech samples using a convolutional neural network (CNN). We carry out experiments on two state-of-the-art ASR models and a large set of acoustic impulse responses (AIRs). The results confirm C50 and C80 to be highly correlated with WER, allowing WER to be predicted with the proposed fitting approaches. The proposed non-intrusive CNN model outperforms C50-based WER prediction, indicating that WER can be estimated blindly, i.e., directly from the reverberant speech samples without knowledge of the acoustic parameters.

This article concerns comparative studies on the Automatic Speech Recognition (ASR) model incorporated with the Large Language Model (LLM) used for medical interviews. The proposed solution is tested on polish language benchmarks and dataset with medical interviews. The latest ASR technologies are based on convolutional neural networks (CNNs), recurrent neural networks (RNNs) and Transformers. Most of them work as end-to-end solutions. The presented approach in the case of the Whisper model shows a two-stage solution with End-To-End ASR and LLM working together in a pipeline. The ASR output is an input for LLM. The LLM is a component by which the output from ASR is corrected and improved. Comparative studies for automatic recognition of the Polish language between modern End-To-End deep learning architectures and the ASR hybrid model were performed. The medical interview tests were performed with two state-of-the-art ASR models: OpenAI Whisper incorporated with LLM and Scribe ElevenLabs. Additionally, the results were compared with five more end-to-end models (QuartzNet, FastConformer, Wav2Vec 2.0 XLSR and ESPnet Model Zoo) on Mozilla Common Voice and VoxPopuli databases. Tests were conducted for clean audio signal, signal with bandwidth limitation, and degraded. The tested models were evaluated on the basis of Word Error Rate (WER) and Character Error Rate (CER). The results show that the Whisper model performs by far the best among the open-source models. ElevenLabs Scribe model, on the other hand, performs best for Polish on both general benchmark and medical data.

This study explores the feasibility of constructing a small-scale speech recognition system capable of competing with larger, modern automated speech recognition (ASR) systems in both performance and word error rate (WER). Our central hypothesis posits that a compact transformer-based ASR model can yield comparable results, specifically in terms of WER, to traditional ASR models while challenging contemporary ASR systems that boast significantly larger computational sizes. The aim is to extend ASR capabilities to under-resourced languages with limited corpora, catering to scenarios where practitioners face constraints in both data availability and computational resources. The model, comprising a compact convolutional neural network (CNN) and transformer architecture with 2.214 million parameters, challenges the conventional wisdom that large-scale transformer-based ASR systems are essential for achieving high accuracy. In comparison, contemporary ASR systems often deploy over 300 million parameters. Trained on a modest dataset of approximately 3000 h – significantly less than the 50,000 h used in larger systems – the proposed model leverages the Common Voice and LibriSpeech datasets. Evaluation on the LibriSpeech test-clean and test-other datasets produced character error rates (CERs) of 6.40% and 16.73% and WERs of 16.03% and 35.51% respectively. Comparisons with existing architectures showcase the efficiency of our model. A gated recurrent unit (GRU) architecture, albeit achieving lower error rates, incurred a computational cost 24 times larger than our proposed model. Large-scale transformer architectures, while achieving marginally lower WERs (2%–4% on LibriSpeech test-clean), require 200 times more parameters and 53,000 additional hours of training data. Modern large language models are used to improve the WERs, but require large computational resources. To further enhance performance, a small 4-g language model was integrated into our end-to-end ASR model, resulting in improved WERs. The overarching goal of this work is to provide a practical solution for practitioners dealing with limited datasets and computational resources, particularly in the context of under-resourced languages.

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.

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.

This work presents a dialect-aware and noise-robust Kannada automatic speech recognition (ASR) system that bridges the gap between low-resource linguistic contexts and state-of-the-art deep learning models. We design a two-stage approach: (i) a scratch-built convolutional neural network (CNN)–Transformer hybrid trained on curated Kannada speech data with fast Fourier transform-based noise reduction and (ii) fine-tuning OpenAI’s Whisper-small model on a dialect-diverse corpus. The proposed pipeline integrates adaptive noise suppression, subword tokenization, and beam-search decoding to handle agglutinative morphology, speaker variation, and environmental noise. Extensive experiments were conducted on two datasets: the Few-shot Learning Evaluation of Universal Representations of Speech (FLEURS) multilingual Kannada subset and a curated 150-sample, Custom-collected Kannada speech dataset covering both formal and conversational speech. On the FLEURS test set (≈ 2.5 hours), our fine-tuned Whisper model achieves a word error rate (WER) of 0.15, a character error rate (CER) of 0.255, and a BLEU score of 0.912, representing a 53% relative reduction in WER and 36% reduction in CER compared to the scratch CNN–Transformer baseline. For the customized dataset, the fine-tuned Whisper model achieves a WER of 0.2311 and a CER of 0.0453, outperforming Google Speech-to-Text Application Programming Interface (API) by 16.8% (relative WER reduction) and surpassing the scratch transformer by over 70% in WER. We further evaluate robustness under dialectal variation and noisy recordings, providing detailed error analysis and computational efficiency metrics. To our knowledge, this is the first comprehensive evaluation of Whisper fine-tuning for Kannada, demonstrating its viability for real-time, edge-deployable applications in education, accessibility, and public administration.

A common metric for evaluating Automatic Speech Recognition (ASR) is Word Error Rate (WER) which solely takes into account discrepancies at the word-level. Although WER is useful, it is not guaranteed to correlate well with intelligibility or performance on downstream tasks that make use of ASR. Meaningful assess- ment of ASR mistakes becomes even more important in high-stake scenarios such as health-care. I propose 2 general measures to evaluate the quality or severity of mistakes made by ASR systems, one based on sentiment analysis and another based on text embeddings. Both have the potential to overcome the limitations of WER. I evaluate these measures on simulated patient-doctor conversations. Measures of severity based on sentiment ratings and text embeddings correlate with human ratings of severity. Measures based on text embeddings have the capability to predict human severity ratings better than WER. These measures are used in metrics in the overall evaluation of 5 ASR engines alongside WER. Results show that these metrics capture characteristics of ASR errors that WER does not. Furthermore, I train an ASR system using severity as a penalty in the loss function and demonstrate the potential for using severity not only in the evaluation, but in the development of ASR. Advantages and limitations of this methodology are analyzed and discussed.

Tone information is very helpful to improve automatic speech recognition (ASR) performance in tonal languages such as Mandarin, Thai, Vietnamese, etc. Since Myanmar language is being considered as a tonal language, the effect of tones on both syllable and word-based ASR performance has been explored. In this work, experiments are done based on the modeling of tones by integrating them into the phoneme set and incorporating them into the Convolutional Neural Network (CNN), state-of-the-art acoustic model. Moreover, to be more effective tone modeling, tonal questions are used to build the phonetic decision tree. With tone information, experiments show that compared with Deep Neural Network (DNN) baseline, the performance of CNN model achieves nearly 2% for word-based ASR or more than 2% for syllable-based ASR improvement over DNN model. As a result, the CNN model with tone information gets 2.43% word error rate (WER) or 2.26% syllable error rate (SER) reductions than without using it.

Deep learning methodologies have had a major impact on performance across a wide variety of machine learning tasks, and speech recognition is no exception. We describe a set of deep learning techniques that proved to be particularly successful in achieving performance gains in word error rate on a popular large vocabulary conversational speech recognition benchmark task (“Switchboard”). We found that the best performance is achieved by combining features from both recurrent and convolutional neural networks. We compare two recurrent architectures: partially unfolded nets with max-out activations and bidirectional long short-term memory nets. In addition, inspired by the success of convolutional networks for image classification, we designed a convolutional net with many convolutional layers and small kernels that create a receptive field with more nonlinearity and fewer parameters than standard configurations. When combined, these neural networks achieve a word error rate of 6.2% on this difficult task; this was the best reported rate at the time of this writing and is even more remarkable given that human performance itself is estimated to be 4% on this data.

Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend

In this paper, an adaptive recognition of different accents conversations is proposed based on Convolutional Neural Network(CNN), which is used to deal with dialogue speech recognition problems that contain different accents in the CALL_CENTER environment. For the first time, the Mel-Frequency Cepstral Coefficients (MFCC) feature and the SPECTROGRAM feature are combined as the input of CNN to train the speakers’ voice feature model and to estimate the change point. Then, an accent classification method based on weighted fusion feature is proposed, and we introduced the IFLY voice recognition system to propose different accent dialogue recognition models based on speaker segmentation. In the experiments, a real database about the dialogue voice related to insurance sales and real estate sales industry is used to be dataset. After a comparative experiment, the results show that the word error rate for speech recognition after speaker segmentation and accent classification was reduced by 20% compared to the original speech recognition word error rate.

Speech recognition in Human-Robot Interaction (HRI) fully relies on audio-based Automatic Speech Recognition. However, speech recognition that relies solely on audio faces significant challenges in noisy environments and may lead to poor performance in such environments. One approach to address this is to also use lipreading in combination with traditional speech recognition. Recent work has shown that audiovisual speech recognition (AVSR) can achieve a Word Error Rate (WER) of only 0.9% on the dataset LRS3. In this paper, we assess the potential of combining audio with lipreading on a social robot platform, Pepper, which has not yet been widely tested for AVSR. Given that prior research has focused on non-robotic domains, it remains unclear whether such models can generalize well to social robot environments. We systematically evaluate and compare the performance of established offline and real-time audiovisual models with their audio-only counterparts. The experiments were conducted in both a controlled laboratory setting and a dynamic and noisy public environment. We evaluated the data using WER and also measured the inference latency of real-time models via Real-Time Factor and Words Per Second rates. The results demonstrate real-time performance for audio-only speech recognition across all latency metrics and near real-time performance for models that combine audio with lipreading. We also explored factors that might influence the inference performance of these models to understand how much video contributes to the audio. This includes factors related to (1) environmental and temporal variations, (2) model behavior, and (3) implementation choices. Our findings indicate that for now the audio-only models outperform the audiovisual models on a social robot platform, in contrast to what has been reported in the benchmarked literature. We conclude that more work is still needed to benefit from lipreading in HRI.

Recently, one of the most common approaches used in speech recognition is deep learning. The most advanced results have been obtained with speech recognition systems created using convolutional neural network (CNN) and recurrent neural networks (RNN). Since CNNs can capture local features effectively, they are applied to tasks with relatively short-term dependencies, such as keyword detection or phoneme- level sequence recognition. This paper presents the development of a deep learning and speech command recognition system. The Google Speech Commands Dataset has been used for training. The dataset contained 65.000 one-second-long words of 30 short English words. That is, %80 of the dataset has been used in the training and %20 of the dataset has been used in the testing. The data set consists of one-second voice commands that have been converted into a spectrogram and used to train different artificial neural network (ANN) models. Various variants of CNN are used in deep learning applications. The performance of the proposed model has reached %94.60.

This study investigates the effect of vowel-reduction dubbing practice on the Word Error Rate (WER) of automatic speech recognition (ASR)-generated captions in Zoom-based English presentations. Employing a convergent mixed-methods design, the research examines how misarticulation related to vowel reduction—particularly the realization of schwa—shapes ASR performance and caption accuracy. Twentyseven English teacher candidates completed structured dubbing tasks followed by ASR transcription analysis using Zoom’s auto-captioning system. WER was calculated using standard computational formulae, and both quantitative data (percentages, accuracy ratios, and error rates) and qualitative data (error types, substitution patterns, and prosodic deviations) were systematically analyzed. Results indicate that substitution errors remained the most dominant ASR error type, especially when vowel reduction occurred without adequate prosodic support. A substantial improvement was observed following the intervention: the average WER decreased by approximately 52% (from 27.4% to 13.2%), demonstrating a strong effect of targeted dubbing practice on caption intelligibility. Participants who maintained clearer vowel quality and rhythmic timing achieved consistently lower WER scores, while those applying excessive or inconsistent vowel reduction produced higher rates of substitution and deletion errors. The study highlights the pedagogical value of integrating ASR-based feedback with dubbing activities to strengthen learners’ pronunciation intelligibility and schwa awareness. It further underscores the importance of TPACK-informed instruction that cultivates learners’ sensitivity to both human comprehensibility and machine recognition. Overall, these findings contribute to ongoing developments in pronunciation pedagogy by bridging technology-enhanced learning with EFL teacher education.

Speech foundation models trained at a massive scale, both in terms of model and data size, result in robust systems capable of performing multiple speech tasks, including automatic speech recognition (ASR).These models transcend language and domain barriers, yet effectively measuring their performance remains a challenge.Traditional metrics like word error rate (WER) and character error rate (CER) are commonly used to evaluate ASR performance but often fail to reflect transcription quality in critical contexts, particularly when detecting fabricated outputs.This phenomenon, known as hallucination, is especially concerning in high-stakes domains such as healthcare, legal, and aviation, where errors can have severe consequences.In our work, we address this gap by investigating hallucination in ASR models.We examine how factors such as distribution shifts, model size, and model architecture influence the hallucination error rate (HER), a metric we introduce to quantify hallucinations.Our analysis of over 20 ASR models reveals three key insights: (1) High WERs can mask low hallucination rates, while low WERs may conceal dangerous hallucinations.(2) Synthetic noise, both adversarial and common perturbations like white noise, pitch shift, and time stretching, increase HER.(3) Distribution shift correlates strongly with HER ( = 0.91).Our findings highlight the importance of incorporating HER alongside traditional metrics like WER to better assess ASR model performance, particularly in high-stakes domains.