Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR application can lead to a lower number of incidents caused by misunderstanding and improve air traffic management (ATM) efficiency. Evidently, high accuracy predictions, especially, of key information, i.e., callsigns and commands, are required to minimize the risk of errors. We prove that combining the benefits of ASR and Natural Language Processing (NLP) methods to make use of surveillance data (i.e. additional modality) helps to considerably improve the recognition of callsigns (named entity). In this paper, we investigate a two-step callsign boosting approach: (1) at the 1 step (ASR), weights of probable callsign n-grams are reduced in G.fst and/or in the decoding FST (lattices), (2) at the 2 step (NLP), callsigns extracted from the improved recognition outputs with Named Entity Recognition (NER) are correlated with the surveillance data to select the most suitable one. Boosting callsign n-grams with the combination of ASR and NLP methods eventually leads up to 53.7% of an absolute, or 60.4% of a relative, improvement in callsign recognition.
Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech. However, studies have suggested to favor a certain type of convolutional operations when building a deep convolutional neural network for speech applications although there has been promising results using different types of convolutional operations. In this work, we study four types of convolutional operations on different input features for speech emotion recognition under noisy and clean conditions in order to derive a comprehensive understanding. Since affective behavioral information has been shown to reflect temporally varying of mental state and convolutional operation are applied locally in time, all deep neural networks share a deep recurrent sub-network architecture for further temporal modeling. We present detailed quantitative module-wise performance analysis to gain insights into information flows within the proposed architectures. In particular, we demonstrate the interplay of affective information and the other irrelevant information during the progression from one module to another. Finally we show that all of our deep neural networks provide state-of-the-art performance on the eNTERFACE'05 corpus.
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-trained acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic representation learning method to fuse and utilize the contextual information of speech and text. Specifically, we unify a pre-trained acoustic model (wav2vec 2.0) and a language model (BERT) into an end-to-end trainable framework. A Representation Aggregation Module is designed to aggregate acoustic and linguistic representation, and an Embedding Attention Module is introduced to incorporate acoustic information into BERT, which can effectively facilitate the cooperation of two pre-trained models and thus boost the representation learning. Extensive experiments show that our Wav-BERT significantly outperforms the existing approaches and achieves state-of-the-art performance on low-resource speech recognition.
Code-switching (CS), defined as the mixing of languages in conversations, has become a worldwide phenomenon. The prevalence of CS has been recently met with a growing demand and interest to build CS ASR systems. In this paper, we present our work on code-switched Egyptian Arabic-English automatic speech recognition (ASR). We first contribute in filling the huge gap in resources by collecting, analyzing and publishing our spontaneous CS Egyptian Arabic-English speech corpus. We build our ASR systems using DNN-based hybrid and Transformer-based end-to-end models. In this paper, we present a thorough comparison between both approaches under the setting of a low-resource, orthographically unstandardized, and morphologically rich language pair. We show that while both systems give comparable overall recognition results, each system provides complementary sets of strength points. We show that recognition can be improved by combining the outputs of both systems. We propose several effective system combination approaches, where hypotheses of both systems are merged on sentence- and word-levels. Our approaches result in overall WER relative improvement of 4.7%, over a baseline performance of 32.1% WER. In the case of intra-sentential CS sentences, we achieve WER relative improvement of 4.8%. Our best performing system achieves 30.6% WER on ArzEn test set.
We propose a novel method for generating scene-aware training data for far-field automatic speech recognition. We use a deep learning-based estimator to non-intrusively compute the sub-band reverberation time of an environment from its speech samples. We model the acoustic characteristics of a scene with its reverberation time and represent it using a multivariate Gaussian distribution. We use this distribution to select acoustic impulse responses from a large real-world dataset for augmenting speech data. The speech recognition system trained on our scene-aware data consistently outperforms the system trained using many more random acoustic impulse responses on the REVERB and the AMI far-field benchmarks. In practice, we obtain 2.64% absolute improvement in word error rate compared with using training data of the same size with uniformly distributed reverberation times.
Speaker recognition is a well known and studied task in the speech processing domain. It has many applications, either for security or speaker adaptation of personal devices. In this paper, we present a new paradigm for automatic speaker recognition that we call Interactive Speaker Recognition (ISR). In this paradigm, the recognition system aims to incrementally build a representation of the speakers by requesting personalized utterances to be spoken in contrast to the standard text-dependent or text-independent schemes. To do so, we cast the speaker recognition task into a sequential decision-making problem that we solve with Reinforcement Learning. Using a standard dataset, we show that our method achieves excellent performance while using little speech signal amounts. This method could also be applied as an utterance selection mechanism for building speech synthesis systems.
Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial speech signals. Specifically, we evaluate the model performance by interpretable speech recognition metrics and discuss the model performance by the augmented adversarial training. Our experiments show that our proposed U-Net$_{At}$ improves the perceptual evaluation of speech quality (PESQ) from 1.13 to 2.78, speech transmission index (STI) from 0.65 to 0.75, short-term objective intelligibility (STOI) from 0.83 to 0.96 on the task of speech enhancement with adversarial speech examples. We conduct experiments on the automatic speech recognition (ASR) task with adversarial audio attacks. We find that (i) temporal features learned by the attention network are capable of enhancing the robustness of DNN based ASR models; (ii) the generalization power of DNN based ASR model could be enhanced by applying adversarial training with an additive adversarial data augmentation. The ASR metric on word-error-rates (WERs) shows that there is an absolute 2.22 $\%$ decrease under gradient-based perturbation, and an absolute 2.03 $\%$ decrease, under evolutionary-optimized perturbation, which suggests that our enhancement models with adversarial training can further secure a resilient ASR system.
Existing approaches to ensuring privacy of user speech data primarily focus on server-side approaches. While improving server-side privacy reduces certain security concerns, users still do not retain control over whether privacy is ensured on the client-side. In this paper, we define, evaluate, and explore techniques for client-side privacy in speech recognition, where the goal is to preserve privacy on raw speech data before leaving the client's device. We first formalize several tradeoffs in ensuring client-side privacy between performance, compute requirements, and privacy. Using our tradeoff analysis, we perform a large-scale empirical study on existing approaches and find that they fall short on at least one metric. Our results call for more research in this crucial area as a step towards safer real-world deployment of speech recognition systems at scale across mobile devices.
In this paper, the Lingban entry to the third 'CHiME' speech separation and recognition challenge is presented. A time-frequency masking based speech enhancement front-end is proposed to suppress the environmental noise utilizing multi-channel coherence and spatial cues. The state-of-the-art speech recognition techniques, namely recurrent neural network based acoustic and language modeling, state space minimum Bayes risk based discriminative acoustic modeling, and i-vector based acoustic condition modeling, are carefully integrated into the speech recognition back-end. To further improve the system performance by fully exploiting the advantages of different technologies, the final recognition results are obtained by lattice combination and rescoring. Evaluations carried out on the official dataset prove the effectiveness of the proposed systems. Comparing with the best baseline result, the proposed system obtains consistent improvements with over 57% relative word error rate reduction on the real-data test set.
Add to Chrome
Add to Firefox