The technology development for point-of-care tests (POCTs) targeting respiratory diseases has witnessed a growing demand in the recent past. Investigating the presence of acoustic biomarkers in modalities such as cough, breathing and speech sounds, and using them for building POCTs can offer fast, contactless and inexpensive testing. In view of this, over the past year, we launched the ``Coswara'' project to collect cough, breathing and speech sound recordings via worldwide crowdsourcing. With this data, a call for development of diagnostic tools was announced in the Interspeech 2021 as a special session titled ``Diagnostics of COVID-19 using Acoustics (DiCOVA) Challenge''. The goal was to bring together researchers and practitioners interested in developing acoustics-based COVID-19 POCTs by enabling them to work on the same set of development and test datasets. As part of the challenge, datasets with breathing, cough, and speech sound samples from COVID-19 and non-COVID-19 individuals were released to the participants. The challenge consisted of two tracks. The Track-1 focused only on cough sounds, and participants competed in a leaderboard setting. In Track-2, breathing and speech samples were provided for the participants, without a competitive leaderboard. The challenge attracted 85 plus registrations with 29 final submissions for Track-1. This paper describes the challenge (datasets, tasks, baseline system), and presents a focused summary of the various systems submitted by the participating teams. An analysis of the results from the top four teams showed that a fusion of the scores from these teams yields an area-under-the-curve of 95.1% on the blind test data. By summarizing the lessons learned, we foresee the challenge overview in this paper to help accelerate technology for acoustic-based POCTs.
Prior works on speech emotion recognition utilize various unsupervised learning approaches to deal with low-resource samples. However, these methods pay less attention to modeling the long-term dynamic dependency, which is important for speech emotion recognition. To deal with this problem, this paper combines the unsupervised representation learning strategy -- Future Observation Prediction (FOP), with transfer learning approaches (such as Fine-tuning and Hypercolumns). To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results demonstrate that our method is superior to currently advanced unsupervised learning strategies.
This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo. Our approach is based on developing an extension for the conventional distortion condition of the adversarial optimization formulation using the Cram\`er integral probability metric. Minimizing over this metric, which measures the discrepancies between original and adversarial samples' distributions, contributes to crafting signals very close to the subspace of legitimate speech recordings. This helps to yield more robust adversarial signals against playback over-the-air without employing neither costly expectation over transformation operations nor static room impulse response simulations. Our approach outperforms other targeted and non-targeted algorithms in terms of word error rate and sentence-level-accuracy with competitive performance on the crafted adversarial signals' quality. Compared to seven other strong white and black-box adversarial attacks, our proposed approach is considerably more resilient against multiple consecutive playbacks over-the-air, corroborating its higher robustness in noisy environments.
Visual speech recognition (VSR) aims to recognise the content of speech based on the lip movements without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development of much more accurate and robust VSR models than ever before. However, these advances are usually due to larger training sets rather than the model design. In this work, we demonstrate that designing better models is equally important to using larger training sets. We propose the addition of prediction-based auxiliary tasks to a VSR model and highlight the importance of hyper-parameter optimisation and appropriate data augmentations. We show that such model works for different languages and outperforms all previous methods trained on publicly available datasets by a large margin. It even outperforms models that were trained on non-publicly available datasets containing up to to 21 times more data. We show furthermore that using additional training data, even in other languages or with automatically generated transcriptions, results in further improvement.
Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure the human error rate on the widely used NIST 2000 test set, and find that our latest automated system has reached human parity. The error rate of professional transcribers is 5.9% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, and 11.3% for the CallHome portion where friends and family members have open-ended conversations. In both cases, our automated system establishes a new state of the art, and edges past the human benchmark, achieving error rates of 5.8% and 11.0%, respectively. The key to our system's performance is the use of various convolutional and LSTM acoustic model architectures, combined with a novel spatial smoothing method and lattice-free MMI acoustic training, multiple recurrent neural network language modeling approaches, and a systematic use of system combination.
Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely incorporated in ASR systems to improve their robustness. This paper proposes a novel auditory model which incorporates psychoacoustics and otoacoustic emissions (OAEs) into ASR. In particular, we successfully implement the frequency-dependent property of psychoacoustic models and effectively improve resulting system performance. We also present a novel double-transform spectrum-analysis technique, which can qualitatively predict ASR performance for different noise types. Detailed theoretical analysis is provided to show the effectiveness of the proposed algorithm. Experiments are carried out on the AURORA2 database and show that the word recognition rate using our proposed feature extraction method is significantly increased over the baseline. Given models trained with clean speech, our proposed method achieves up to 85.39% word recognition accuracy on noisy data.
We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling. BeamTransformer seeks to optimize modeling of sequential relationship among signals from different spatial direction. Overlapping speech detection is one of the tasks where such optimization is favorable. In this paper we effectively apply BeamTransformer to detect overlapping segments. Comparing to single-channel approach, BeamTransformer exceeds in learning to identify the relationship among different beam sequences and hence able to make predictions not only from the acoustic signals but also the localization of the source. The results indicate that a successful incorporation of microphone array signals can lead to remarkable gains. Moreover, BeamTransformer takes one step further, as speech from overlapped speakers have been internally separated into different beams.
Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates the text of the source language, and the translation decoder obtains the final translations based on the output of the recognition decoder. Because whether the output of the recognition decoder has the correct semantics is more critical than its accuracy, we propose to improve the multitask ST model by utilizing word embedding as the intermediate.
In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another language (i.e. French) giving 12.6% relative WER reduction.
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother. We also observe competitive performance of 2.7%/6.3% with a small model of only 10M parameters.