In this paper we proposed a novel Adversarial Training (AT) approach for end-to-end speech recognition using a Criticizing Language Model (CLM). In this way the CLM and the automatic speech recognition (ASR) model can challenge and learn from each other iteratively to improve the performance. Since the CLM only takes the text as input, huge quantities of unpaired text data can be utilized in this approach within end-to-end training. Moreover, AT can be applied to any end-to-end ASR model using any deep-learning-based language modeling frameworks, and compatible with any existing end-to-end decoding method. Initial results with an example experimental setup demonstrated the proposed approach is able to gain consistent improvements efficiently from auxiliary text data under different scenarios.
Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other errata common in spoken communication. Many downstream tasks and human readers rely on the output of the ASR system; therefore, errors introduced by the speaker and ASR system alike will be propagated to the next task in the pipeline. In this work, we propose a novel NLP task called ASR post-processing for readability (APR) that aims to transform the noisy ASR output into a readable text for humans and downstream tasks while maintaining the semantic meaning of the speaker. In addition, we describe a method to address the lack of task-specific data by synthesizing examples for the APR task using the datasets collected for Grammatical Error Correction (GEC) followed by text-to-speech (TTS) and ASR. Furthermore, we propose metrics borrowed from similar tasks to evaluate performance on the APR task. We compare fine-tuned models based on several open-sourced and adapted pre-trained models with the traditional pipeline method. Our results suggest that finetuned models improve the performance on the APR task significantly, hinting at the potential benefits of using APR systems. We hope that the read, understand, and rewrite approach of our work can serve as a basis that many NLP tasks and human readers can benefit from.
Controlling a robot still requires traditional user interfaces. A more intuitive approach is using verbal or gesture commands. In this paper, we propose a robotic arm that can recognize the human voice commands. The Speech recognition is an essential asset for the robot, enhancing its ability to interact with human beings using their natural form of communication. The approach is verified by deploying the robotic arm into different environments with low, high and medium noise perturbations, where it is tested to perform a set of tasks. With this approach, we have successfully reduced the response time, enhanced the accuracy of the robotic arm to grasp the voice commands and reduced the sentence overlapping by a significant amount. The entire system is divided into three modules: the manipulator, the voice recognition module and the microcontroller. The robotic arm is programmed to orient to the direction where the signal to noise ratio is maximum.
In this paper, a new speech feature fusion method is proposed for speaker recognition on the basis of the cross gate parallel convolutional neural network (CG-PCNN). The Mel filter bank features (MFBFs) of different frequency resolutions can be extracted from each speech frame of a speaker's speech by several Mel filter banks, where the numbers of the triangular filters in the Mel filter banks are different. Due to the frequency resolutions of these MFBFs are different, there are some complementaries for these MFBFs. The CG-PCNN is utilized to extract the deep features from these MFBFs, which applies a cross gate mechanism to capture the complementaries for improving the performance of the speaker recognition system. Then, the fusion feature can be obtained by concatenating these deep features for speaker recognition. The experimental results show that the speaker recognition system with the proposed speech feature fusion method is effective, and marginally outperforms the existing state-of-the-art systems.
We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model by leveraging unlabelled data. Key to our approach are a strong baseline acoustic and language model used to generate the pseudo-labels, a robust and stable beam-search decoder, and a novel ensemble approach used to increase pseudo-label diversity. Experiments on the LibriSpeech corpus show that self-training with a single model can yield a 21% relative WER improvement on clean data over a baseline trained on 100 hours of labelled data. We also evaluate label filtering approaches to increase pseudo-label quality. With an ensemble of six models in conjunction with label filtering, self-training yields a 26% relative improvement and bridges 55.6% of the gap between the baseline and an oracle model trained with all of the labels.
Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and delay progression. Speech based automatic AD screening systems provide a non-intrusive and more scalable alternative to other clinical screening techniques. Scarcity of such specialist data leads to uncertainty in both model selection and feature learning when developing such systems. To this end, this paper investigates the use of feature and model combination approaches to improve the robustness of domain fine-tuning of BERT and Roberta pre-trained text encoders on limited data, before the resulting embedding features being fed into an ensemble of backend classifiers to produce the final AD detection decision via majority voting. Experiments conducted on the ADReSS20 Challenge dataset suggest consistent performance improvements were obtained using model and feature combination in system development. State-of-the-art AD detection accuracies of 91.67 percent and 93.75 percent were obtained using manual and ASR speech transcripts respectively on the ADReSS20 test set consisting of 48 elderly speakers.
Transcribing voice communications in NASA's launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch control center will help the machine analyze information and accelerate knowledge generation.
In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. This efficient rescoring process causes very little sentence-level latency. Our experiments on the open 170-hour AISHELL-1 dataset show that, the proposed method can unify the streaming and non-streaming model simply and efficiently. On the AISHELL-1 test set, our unified model achieves 5.60% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. The same model achieves 5.42% CER with 640ms latency in a streaming ASR system.
Quantifying the confidence (or conversely the uncertainty) of a prediction is a highly desirable trait of an automatic system, as it improves the robustness and usefulness in downstream tasks. In this paper we investigate confidence estimation for end-to-end automatic speech recognition (ASR). Previous work has addressed confidence measures for lattice-based ASR, while current machine learning research mostly focuses on confidence measures for unstructured deep learning. However, as the ASR systems are increasingly being built upon deep end-to-end methods, there is little work that tries to develop confidence measures in this context. We fill this gap by providing an extensive benchmark of popular confidence methods on four well-known speech datasets. There are two challenges we overcome in adapting existing methods: working on structured data (sequences) and obtaining confidences at a coarser level than the predictions (words instead of tokens). Our results suggest that a strong baseline can be obtained by scaling the logits by a learnt temperature, followed by estimating the confidence as the negative entropy of the predictive distribution and, finally, sum pooling to aggregate at word level.
This Signal Processing Grand Challenge (SPGC) targets a difficult automatic prediction problem of societal and medical relevance, namely, the detection of Alzheimer's Dementia (AD). Participants were invited to employ signal processing and machine learning methods to create predictive models based on spontaneous speech data. The Challenge has been designed to assess the extent to which predictive models built based on speech in one language (English) generalise to another language (Greek). To the best of our knowledge no work has investigated acoustic features of the speech signal in multilingual AD detection. Our baseline system used conventional machine learning algorithms with Active Data Representation of acoustic features, achieving accuracy of 73.91% on AD detection, and 4.95 root mean squared error on cognitive score prediction.