Although the UA-Speech and TORGO databases of control and dysarthric speech are invaluable resources made available to the research community with the objective of developing robust automatic speech recognition systems, they have also been used to validate a considerable number of automatic dysarthric speech classification approaches. Such approaches typically rely on the underlying assumption that recordings from control and dysarthric speakers are collected in the same noiseless environment using the same recording setup. In this paper, we show that this assumption is violated for the UA-Speech and TORGO databases. Using voice activity detection to extract speech and non-speech segments, we show that the majority of state-of-the-art dysarthria classification approaches achieve the same or a considerably better performance when using the non-speech segments of these databases than when using the speech segments. These results demonstrate that such approaches trained and validated on the UA-Speech and TORGO databases are potentially learning characteristics of the recording environment or setup rather than dysarthric speech characteristics. We hope that these results raise awareness in the research community about the importance of the quality of recordings when developing and evaluating automatic dysarthria classification approaches.
Although automatic speech recognition (ASR) can perform well in common non-overlapping environments, sustaining performance in multi-speaker overlapping speech recognition remains challenging. Recent research revealed that ASR model's encoder captures different levels of information with different layers -- the lower layers tend to have more acoustic information, and the upper layers more linguistic. This inspires us to develop a Sidecar separator to empower a well-trained ASR model for multi-speaker scenarios by separating the mixed speech embedding between two suitable layers. We experimented with a wav2vec 2.0-based ASR model with a Sidecar mounted. By freezing the parameters of the original model and training only the Sidecar (8.7 M, 8.4% of all parameters), the proposed approach outperforms the previous state-of-the-art by a large margin for the 2-speaker mixed LibriMix dataset, reaching a word error rate (WER) of 10.36%; and obtains comparable results (7.56%) for LibriSpeechMix dataset when limited training.
Electroencephalography (EEG) plays a vital role in detecting how brain responses to different stimulus. In this paper, we propose a novel Shallow-Deep Attention-based Network (SDANet) to classify the correct auditory stimulus evoking the EEG signal. It adopts the Attention-based Correlation Module (ACM) to discover the connection between auditory speech and EEG from global aspect, and the Shallow-Deep Similarity Classification Module (SDSCM) to decide the classification result via the embeddings learned from the shallow and deep layers. Moreover, various training strategies and data augmentation are used to boost the model robustness. Experiments are conducted on the dataset provided by Auditory EEG challenge (ICASSP Signal Processing Grand Challenge 2023). Results show that the proposed model has a significant gain over the baseline on the match-mismatch track.
Automatic speech recognition (ASR) systems based on deep neural networks are weak against adversarial perturbations. We propose mixPGD adversarial training method to improve the robustness of the model for ASR systems. In standard adversarial training, adversarial samples are generated by leveraging supervised or unsupervised methods. We merge the capabilities of both supervised and unsupervised approaches in our method to generate new adversarial samples which aid in improving model robustness. Extensive experiments and comparison across various state-of-the-art defense methods and adversarial attacks have been performed to show that mixPGD gains 4.1% WER of better performance than previous best performing models under white-box adversarial attack setting. We tested our proposed defense method against both white-box and transfer based black-box attack settings to ensure that our defense strategy is robust against various types of attacks. Empirical results on several adversarial attacks validate the effectiveness of our proposed approach.
As dialogue systems are becoming more and more interactional and social, also the accurate automatic speech recognition (ASR) of conversational speech is of increasing importance. This shifts the focus from short, spontaneous, task-oriented dialogues to the much higher complexity of casual face-to-face conversations. However, the collection and annotation of such conversations is a time-consuming process and data is sparse for this specific speaking style. This paper presents ASR experiments with read and conversational Austrian German as target. In order to deal with having only limited resources available for conversational German and, at the same time, with a large variation among speakers with respect to pronunciation characteristics, we improve a Kaldi-based ASR system by incorporating a (large) knowledge-based pronunciation lexicon, while exploring different data-based methods to restrict the number of pronunciation variants for each lexical entry. We achieve best WER of 0.4% on Austrian German read speech and best average WER of 48.5% on conversational speech. We find that by using our best pronunciation lexicon a similarly high performance can be achieved than by increasing the size of the data used for the language model by approx. 360% to 760%. Our findings indicate that for low-resource scenarios -- despite the general trend in speech technology towards using data-based methods only -- knowledge-based approaches are a successful, efficient method.
Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks.
Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It enables learning the relations between input and output sequences, termed alignments, by marginalizing over perfect alignments (that yield the ground truth), at the expense of imperfect alignments. This binary differentiation of perfect and imperfect alignments falls short of capturing other essential alignment properties that hold significance in other real-world applications. Here we propose $\textit{Align With Purpose}$, a $\textbf{general Plug-and-Play framework}$ for enhancing a desired property in models trained with the CTC criterion. We do that by complementing the CTC with an additional loss term that prioritizes alignments according to a desired property. Our method does not require any intervention in the CTC loss function, enables easy optimization of a variety of properties, and allows differentiation between both perfect and imperfect alignments. We apply our framework in the domain of Automatic Speech Recognition (ASR) and show its generality in terms of property selection, architectural choice, and scale of training dataset (up to 280,000 hours). To demonstrate the effectiveness of our framework, we apply it to two unrelated properties: emission time and word error rate (WER). For the former, we report an improvement of up to 570ms in latency optimization with a minor reduction in WER, and for the latter, we report a relative improvement of 4.5% WER over the baseline models. To the best of our knowledge, these applications have never been demonstrated to work on a scale of data as large as ours. Notably, our method can be implemented using only a few lines of code, and can be extended to other alignment-free loss functions and to domains other than ASR.
We introduce Multi-level feature Fusion-based Periodicity Analysis Model (MF-PAM), a novel deep learning-based pitch estimation model that accurately estimates pitch trajectory in noisy and reverberant acoustic environments. Our model leverages the periodic characteristics of audio signals and involves two key steps: extracting pitch periodicity using periodic non-periodic convolution (PNP-Conv) blocks and estimating pitch by aggregating multi-level features using a modified bi-directional feature pyramid network (BiFPN). We evaluate our model on speech and music datasets and achieve superior pitch estimation performance compared to state-of-the-art baselines while using fewer model parameters. Our model achieves 99.20 % accuracy in pitch estimation on a clean musical dataset. Overall, our proposed model provides a promising solution for accurate pitch estimation in challenging acoustic environments and has potential applications in audio signal processing.
Multimodal corpora have become an essential language resource for language science and grounded natural language processing (NLP) systems due to the growing need to understand and interpret human communication across various channels. In this paper, we first present our efforts in building the first Multimodal Corpus for Languages in Taiwan (MultiMoco). Based on the corpus, we conduct a case study investigating the Lexical Retrieval Hypothesis (LRH), specifically examining whether the hand gestures co-occurring with speech constants facilitate lexical retrieval or serve other discourse functions. With detailed annotations on eight parliamentary interpellations in Taiwan Mandarin, we explore the co-occurrence between speech constants and non-verbal features (i.e., head movement, face movement, hand gesture, and function of hand gesture). Our findings suggest that while hand gestures do serve as facilitators for lexical retrieval in some cases, they also serve the purpose of information emphasis. This study highlights the potential of the MultiMoco Corpus to provide an important resource for in-depth analysis and further research in multimodal communication studies.
In this paper, we explore the application of language and speech technology to open-ended questions in a Dutch panel survey. In an experimental wave respondents could choose to answer open questions via speech or keyboard. Automatic speech recognition (ASR) was used to process spoken responses. We evaluated answers from these input modalities to investigate differences between spoken and typed answers.We report the errors the ASR system produces and investigate the impact of these errors on downstream analyses. Open-ended questions give more freedom to answer for respondents, but entail a non-trivial amount of work to analyse. We evaluated the feasibility of using transformer-based models (e.g. BERT) to apply sentiment analysis and topic modelling on the answers of open questions. A big advantage of transformer-based models is that they are trained on a large amount of language materials and do not necessarily need training on the target materials. This is especially advantageous for survey data, which does not contain a lot of text materials. We tested the quality of automatic sentiment analysis by comparing automatic labeling with three human raters and tested the robustness of topic modelling by comparing the generated models based on automatic and manually transcribed spoken answers.