In the rapidly evolving landscape of medical documentation, transcribing clinical dialogues accurately is increasingly paramount. This study explores the potential of Large Language Models (LLMs) to enhance the accuracy of Automatic Speech Recognition (ASR) systems in medical transcription. Utilizing the PriMock57 dataset, which encompasses a diverse range of primary care consultations, we apply advanced LLMs to refine ASR-generated transcripts. Our research is multifaceted, focusing on improvements in general Word Error Rate (WER), Medical Concept WER (MC-WER) for the accurate transcription of essential medical terms, and speaker diarization accuracy. Additionally, we assess the role of LLM post-processing in improving semantic textual similarity, thereby preserving the contextual integrity of clinical dialogues. Through a series of experiments, we compare the efficacy of zero-shot and Chain-of-Thought (CoT) prompting techniques in enhancing diarization and correction accuracy. Our findings demonstrate that LLMs, particularly through CoT prompting, not only improve the diarization accuracy of existing ASR systems but also achieve state-of-the-art performance in this domain. This improvement extends to more accurately capturing medical concepts and enhancing the overall semantic coherence of the transcribed dialogues. These findings illustrate the dual role of LLMs in augmenting ASR outputs and independently excelling in transcription tasks, holding significant promise for transforming medical ASR systems and leading to more accurate and reliable patient records in healthcare settings.
Punctuation restoration is a crucial step after Automatic Speech Recognition (ASR) systems to enhance transcript readability and facilitate subsequent NLP tasks. Nevertheless, conventional lexical-based approaches are inadequate for solving the punctuation restoration task in Spanish, where ambiguity can be often found between unpunctuated declaratives and questions. In this study, we propose a novel hybrid acoustic-lexical punctuation restoration system for Spanish transcription, which consolidates acoustic and lexical signals through a modular process. Our experiment results show that the proposed system can effectively improve F1 score of question marks and overall punctuation restoration on both public and internal Spanish conversational datasets. Additionally, benchmark comparison against LLMs (Large Language Model) indicates the superiority of our approach in accuracy, reliability and latency. Furthermore, we demonstrate that the Word Error Rate (WER) of the ASR module also benefits from our proposed system.
In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the look-ahead and past contexts in the encoder, and (2) introducing an activation caching mechanism to enable the non-autoregressive encoder to operate autoregressively during inference. The proposed model is thoughtfully designed in a way to eliminate the accuracy disparity between the train and inference time which is common for many streaming models. Furthermore, our proposed encoder works with various decoder configurations including Connectionist Temporal Classification (CTC) and RNN-Transducer (RNNT) decoders. Additionally, we introduced a hybrid CTC/RNNT architecture which utilizes a shared encoder with both a CTC and RNNT decoder to boost the accuracy and save computation. We evaluate the proposed model on LibriSpeech dataset and a multi-domain large scale dataset and demonstrate that it can achieve better accuracy with lower latency and inference time compared to a conventional buffered streaming model baseline. We also showed that training a model with multiple latencies can achieve better accuracy than single latency models while it enables us to support multiple latencies with a single model. Our experiments also showed the hybrid architecture would not only speedup the convergence of the CTC decoder but also improves the accuracy of streaming models compared to single decoder models.
In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without ground-truth labels is still challenging. A previous study has shown the effectiveness of using ensemble teacher models in T/S training for unsupervised domain adaptation (UDA) but its performance still lags behind compared to the model trained on in-domain data. This paper proposes a method to yield better UDA by training multi-stage students with ensemble teacher models. Initially, multiple teacher models are trained on labelled data from read and meeting domains. These teachers are used to train a student model on unlabelled out-of-domain telephone speech data. To improve the adaptation, subsequent student models are trained sequentially considering previously trained model as their teacher. Experiments are conducted with three teachers trained on AMI, WSJ and LibriSpeech and three stages of students on SwitchBoard data. Results shown on eval00 test set show significant WER improvement with multi-stage training with an absolute gain of 9.8%, 7.7% and 3.3% at each stage.
Recently audio-visual speech recognition (AVSR), which better leverages video modality as additional information to extend automatic speech recognition (ASR), has shown promising results in complex acoustic environments. However, there is still substantial space to improve as complex computation of visual modules and ineffective fusion of audio-visual modalities. To eliminate these drawbacks, we propose a down-up sampling-based AVSR model (Hourglass-AVSR) to enjoy high efficiency and performance, whose time length is scaled during the intermediate processing, resembling an hourglass. Firstly, we propose a context and residual aware video upsampling approach to improve the recognition performance, which utilizes contextual information from visual representations and captures residual information between adjacent video frames. Secondly, we introduce a visual-audio alignment approach during the upsampling by explicitly incorporating boundary constraint loss. Besides, we propose a cross-layer attention fusion to capture the modality dependencies within each visual encoder layer. Experiments conducted on the MISP-AVSR dataset reveal that our proposed Hourglass-AVSR model outperforms ASR model by 12.9% and 20.8% relative concatenated minimum permutation character error rate (cpCER) reduction on far-field and middle-field test sets, respectively. Moreover, compared to other state-of-the-art AVSR models, our model exhibits the highest improvement in cpCER for the visual module. Furthermore, on the benefit of our down-up sampling approach, Hourglass-AVSR model reduces 54.2% overall computation costs with minor performance degradation.
Recurrent neural networks (RNNs) have emerged as powerful tools for processing sequential data in various fields, including natural language processing and speech recognition. However, the lack of explainability in RNN models has limited their interpretability, posing challenges in understanding their internal workings. To address this issue, this paper proposes a methodology for extracting a state machine (SM) from an RNN-based model to provide insights into its internal function. The proposed SM extraction algorithm was assessed using four newly proposed metrics: Purity, Richness, Goodness, and Scale. The proposed methodology along with its assessment metrics contribute to increasing explainability in RNN models by providing a clear representation of their internal decision making process through the extracted SM. In addition to improving the explainability of RNNs, the extracted SM can be used to advance testing and and monitoring of the primary RNN-based model. To enhance RNN testing, we introduce six model coverage criteria based on the extracted SM, serving as metrics for evaluating the effectiveness of test suites designed to analyze the primary model. We also propose a tree-based model to predict the error probability of the primary model for each input based on the extracted SM. We evaluated our proposed online error prediction approach using the MNIST dataset and Mini Speech Commands dataset, achieving an area under the curve (AUC) exceeding 80\% for the receiver operating characteristic (ROC) chart.
Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is represented by a segment of speech signal with variable length and unknown boundary, and this segmental structure makes learning the mapping between speech and text challenging, especially without paired data. In this paper, we propose REBORN, Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR. REBORN alternates between (1) training a segmentation model that predicts the boundaries of the segmental structures in speech signals and (2) training the phoneme prediction model, whose input is a segmental structure segmented by the segmentation model, to predict a phoneme transcription. Since supervised data for training the segmentation model is not available, we use reinforcement learning to train the segmentation model to favor segmentations that yield phoneme sequence predictions with a lower perplexity. We conduct extensive experiments and find that under the same setting, REBORN outperforms all prior unsupervised ASR models on LibriSpeech, TIMIT, and five non-English languages in Multilingual LibriSpeech. We comprehensively analyze why the boundaries learned by REBORN improve the unsupervised ASR performance.
In this work, we present VNLP: the first dedicated, complete, open-source, well-documented, lightweight, production-ready, state-of-the-art Natural Language Processing (NLP) package for the Turkish language. It contains a wide variety of tools, ranging from the simplest tasks, such as sentence splitting and text normalization, to the more advanced ones, such as text and token classification models. Its token classification models are based on "Context Model", a novel architecture that is both an encoder and an auto-regressive model. NLP tasks solved by VNLP models include but are not limited to Sentiment Analysis, Named Entity Recognition, Morphological Analysis \& Disambiguation and Part-of-Speech Tagging. Moreover, it comes with pre-trained word embeddings and corresponding SentencePiece Unigram tokenizers. VNLP has an open-source GitHub repository, ReadtheDocs documentation, PyPi package for convenient installation, Python and command-line API and a demo page to test all the functionality. Consequently, our main contribution is a complete, compact, easy-to-install and easy-to-use NLP package for Turkish.
Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as Automatic Speech Recognition (ASR), and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement. In this paper, we introduce AIR-Bench (\textbf{A}udio \textbf{I}nst\textbf{R}uction \textbf{Bench}mark), the first benchmark designed to evaluate the ability of LALMs to understand various types of audio signals (including human speech, natural sounds, and music), and furthermore, to interact with humans in the textual format. AIR-Bench encompasses two dimensions: \textit{foundation} and \textit{chat} benchmarks. The former consists of 19 tasks with approximately 19k single-choice questions, intending to inspect the basic single-task ability of LALMs. The latter one contains 2k instances of open-ended question-and-answer data, directly assessing the comprehension of the model on complex audio and its capacity to follow instructions. Both benchmarks require the model to generate hypotheses directly. We design a unified framework that leverages advanced language models, such as GPT-4, to evaluate the scores of generated hypotheses given the meta-information of the audio. Experimental results demonstrate a high level of consistency between GPT-4-based evaluation and human evaluation. By revealing the limitations of existing LALMs through evaluation results, AIR-Bench can provide insights into the direction of future research.
In multilingual speech recognition systems, a situation can often arise when the language is not known in advance, but the signal has already been received and is being processed. For such cases, some generalized model is needed that will be able to respond to phonetic differences and, depending on them, correctly recog-nize speech in the desired language. To build such a model, it is necessary to set the values of phonetic parameters, and then compare similar sounds, establishing significant differences.