In this work, we propose novel decoding algorithms to enable streaming automatic speech recognition (ASR) on unsegmented long-form recordings without voice activity detection (VAD), based on monotonic chunkwise attention (MoChA) with an auxiliary connectionist temporal classification (CTC) objective. We propose a block-synchronous beam search decoding to take advantage of efficient batched output-synchronous and low-latency input-synchronous searches. We also propose a VAD-free inference algorithm that leverages CTC probabilities to determine a suitable timing to reset the model states to tackle the vulnerability to long-form data. Experimental evaluations demonstrate that the block-synchronous decoding achieves comparable accuracy to the label-synchronous one. Moreover, the VAD-free inference can recognize long-form speech robustly for up to a few hours.
Nowadays, neural vocoders can generate very high-fidelity speech when a bunch of training data is available. Although a speaker-dependent (SD) vocoder usually outperforms a speaker-independent (SI) vocoder, it is impractical to collect a large amount of data of a specific target speaker for most real-world applications. To tackle the problem of limited target data, a data augmentation method based on speaker representation and similarity measurement of speaker verification is proposed in this paper. The proposed method selects utterances that have similar speaker identity to the target speaker from an external corpus, and then combines the selected utterances with the limited target data for SD vocoder adaptation. The evaluation results show that, compared with the vocoder adapted using only limited target data, the vocoder adapted using augmented data improves both the quality and similarity of synthesized speech.
Many commercial and forensic applications of speech demand the extraction of information about the speaker characteristics, which falls into the broad category of speaker profiling. The speaker characteristics needed for profiling include physical traits of the speaker like height, age, and gender of the speaker along with the native language of the speaker. Many of the datasets available have only partial information for speaker profiling. In this paper, we attempt to overcome this limitation by developing a new dataset which has speech data from five different Indian languages along with English. The metadata information for speaker profiling applications like linguistic information, regional information, and physical characteristics of a speaker are also collected. We call this dataset as NITK-IISc Multilingual Multi-accent Speaker Profiling (NISP) dataset. The description of the dataset, potential applications, and baseline results for speaker profiling on this dataset are provided in this paper.
Several changes occur in the brain in response to voluntary and involuntary activities performed by a person. The ability to retrieve data from the brain within a time space provides basis for in-depth analyses that offer insight on what changes occur in the brain during its decision making processes. In this work, we present the technical description and software implementation of an electroencephalographic (EEG) based intelligent communication system. We use EEG dry sensors to read brain waves data in real-time with which we compute the likelihood that a voluntary eye blink has been made by a person and use the decision to trigger buttons on a user interface in order to produce text using a modification of the T9 algorithm. Our results indicate that EEG-based technology can be effectively applied in facilitating speech for people with severe speech and muscular disabilities, providing a foundation for future work in the area.
Distracted driving is deadly, claiming 3,477 lives in the U.S. in 2015 alone. Although there has been a considerable amount of research on modeling the distracted behavior of drivers under various conditions, accurate automatic detection using multiple modalities and especially the contribution of using the speech modality to improve accuracy has received little attention. This paper introduces a new multimodal dataset for distracted driving behavior and discusses automatic distraction detection using features from three modalities: facial expression, speech and car signals. Detailed multimodal feature analysis shows that adding more modalities monotonically increases the predictive accuracy of the model. Finally, a simple and effective multimodal fusion technique using a polynomial fusion layer shows superior distraction detection results compared to the baseline SVM and neural network models.
Emotion recognition has become an important field of research in Human Computer Interactions as we improve upon the techniques for modelling the various aspects of behaviour. With the advancement of technology our understanding of emotions are advancing, there is a growing need for automatic emotion recognition systems. One of the directions the research is heading is the use of Neural Networks which are adept at estimating complex functions that depend on a large number and diverse source of input data. In this paper we attempt to exploit this effectiveness of Neural networks to enable us to perform multimodal Emotion recognition on IEMOCAP dataset using data from Speech, Text, and Motion capture data from face expressions, rotation and hand movements. Prior research has concentrated on Emotion detection from Speech on the IEMOCAP dataset, but our approach is the first that uses the multiple modes of data offered by IEMOCAP for a more robust and accurate emotion detection.
Spoken content processing (such as retrieval and browsing) is maturing, but the singing content is still almost completely left out. Songs are human voice carrying plenty of semantic information just as speech, and may be considered as a special type of speech with highly flexible prosody. The various problems in song audio, for example the significantly changing phone duration over highly flexible pitch contours, make the recognition of lyrics from song audio much more difficult. This paper reports an initial attempt towards this goal. We collected music-removed version of English songs directly from commercial singing content. The best results were obtained by TDNN-LSTM with data augmentation with 3-fold speed perturbation plus some special approaches. The WER achieved (73.90%) was significantly lower than the baseline (96.21%), but still relatively high.
Object referring has important applications, especially for human-machine interaction. While having received great attention, the task is mainly attacked with written language (text) as input rather than spoken language (speech), which is more natural. This paper investigates Object Referring with Spoken Language (ORSpoken) by presenting two datasets and one novel approach. Objects are annotated with their locations in images, text descriptions and speech descriptions. This makes the datasets ideal for multi-modality learning. The approach is developed by carefully taking down ORSpoken problem into three sub-problems and introducing task-specific vision-language interactions at the corresponding levels. Experiments show that our method outperforms competing methods consistently and significantly. The approach is also evaluated in the presence of audio noise, showing the efficacy of the proposed vision-language interaction methods in counteracting background noise.
Word embeddings are a powerful approach for analyzing language, and exponential family embeddings (EFE) extend them to other types of data. Here we develop structured exponential family embeddings (S-EFE), a method for discovering embeddings that vary across related groups of data. We study how the word usage of U.S. Congressional speeches varies across states and party affiliation, how words are used differently across sections of the ArXiv, and how the co-purchase patterns of groceries can vary across seasons. Key to the success of our method is that the groups share statistical information. We develop two sharing strategies: hierarchical modeling and amortization. We demonstrate the benefits of this approach in empirical studies of speeches, abstracts, and shopping baskets. We show how S-EFE enables group-specific interpretation of word usage, and outperforms EFE in predicting held-out data.
Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and time consuming task. Its success in the fields of computer vision and natural language processing have prompted its recent adoption into the field of audio and speech processing. Comprehensive reviews summarising the knowledge in audio SSL are currently missing. To fill this gap, in the present work, we provide an overview of the SSL methods used for audio and speech processing applications. Herein, we also summarise the empirical works that exploit the audio modality in multi-modal SSL frameworks, and the existing suitable benchmarks to evaluate the power of SSL in the computer audition domain. Finally, we discuss some open problems and point out the future directions on the development of audio SSL.