Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices, but also enables people to express anti-social behavior like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behavior analysis, by predicting the contexts mostly for highly-resourced languages like English. However, some languages such as Bengali are under-resourced that lack of computational resources for natural language processing(NLP). In this paper, we propose an explainable approach for hate speech detection from under-resourced Bengali language, which we called DeepHateExplainer. In our approach, Bengali texts are first comprehensively preprocessed, before classifying them into political, personal, geopolitical, and religious hates, by employing neural ensemble of different transformer-based neural architectures(i.e., monolingual Bangla BERT-base, multilingual BERT-cased and uncased, and XLM-RoBERTa), followed by identifying important terms with sensitivity analysis and layer-wise relevance propagation(LRP) to provide human-interpretable explanations. Evaluations against several machine learning~(linear and tree-based models) and deep neural networks (i.e., CNN, Bi-LSTM, and Conv-LSTM with word embeddings) baselines yield F1 scores of 84%, 90%, 88%, and 88%, for political, personal, geopolitical, and religious hates, respectively, during 3-fold cross-validation tests.
We estimate articulatory movements in speech production from different modalities - acoustics and phonemes. Acoustic-to articulatory inversion (AAI) is a sequence-to-sequence task. On the other hand, phoneme to articulatory (PTA) motion estimation faces a key challenge in reliably aligning the text and the articulatory movements. To address this challenge, we explore the use of a transformer architecture - FastSpeech, with explicit duration modelling to learn hard alignments between the phonemes and articulatory movements. We also train a transformer model on AAI. We use correlation coefficient (CC) and root mean squared error (rMSE) to assess the estimation performance in comparison to existing methods on both tasks. We observe 154%, 11.8% & 4.8% relative improvement in CC with subject-dependent, pooled and fine-tuning strategies, respectively, for PTA estimation. Additionally, on the AAI task, we obtain 1.5%, 3% and 3.1% relative gain in CC on the same setups compared to the state-of-the-art baseline. We further present the computational benefits of having transformer architecture as representation blocks.
In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a label. However, the imperfect ASR result makes unsupervised learning difficult to consistently improve recognition performance especially in the case that multiple powerful teacher models are unavailable. In contrast to conventional unsupervised learning approaches, we adopt the \emph{multi-task learning} (MTL) framework where the $n$-th best ASR hypothesis is used as the label of each task. The seq2seq network is updated through the MTL framework so as to find the common representation that can cover multiple hypotheses. By doing so, the effect of the \emph{hard-decision} errors can be alleviated. We first demonstrate the effectiveness of our self-learning methods through ASR experiments in an accent adaptation task between the US and British English speech. Our experiment results show that our method can reduce the WER on the British speech data from 14.55\% to 10.36\% compared to the baseline model trained with the US English data only. Moreover, we investigate the effect of our proposed methods in a federated learning scenario.
For Automatic Speech Recognition (ASR), the CTC-based methods have become a dominant paradigm due to its simple architecture and efficient non-autoregressive inference manner. However, these methods without external language models usually lack the capacity of modeling the conditional dependencies and the textual interaction. In this work, we present a Gated Interlayer Collaboration (GIC) mechanism which introduces the contextual information into the models and relaxes the conditional independence assumption of the CTC-based models. Specifically, we train the model with intermediate CTC losses calculated by the interlayer outputs of the model, in which the probability distributions of the intermediate layers naturally serve as soft label sequences. The GIC block consists of an embedding layer to obtain the textual embedding of the soft label at each position, and a gate unit to fuse the textual embedding and the acoustic features. Experiments on AISHELL-1 and AIDATATANG benchmarks show that the proposed method outperforms the recently published CTC-based ASR models. Specifically, our method achieves CER of 4.0%/4.4% on AISHELL-1 dev/test sets and CER of 3.8%/4.4% on AIDATATANG dev/test sets using CTC greedy search decoding without external language models.
During speech, people spontaneously gesticulate, which plays a key role in conveying information. Similarly, realistic co-speech gestures are crucial to enable natural and smooth interactions with social agents. Current data-driven co-speech gesture generation systems use a single modality for representing speech: either audio or text. These systems are therefore confined to producing either acoustically-linked beat gestures or semantically-linked gesticulation (e.g., raising a hand when saying ``high''): they cannot appropriately learn to generate both gesture types. We present a model designed to produce arbitrary beat and semantic gestures together. Our deep-learning based model takes both acoustic and semantic representations of speech as input, and generates gestures as a sequence of joint angle rotations as output. The resulting gestures can be applied to both virtual agents and humanoid robots. We illustrate the model's efficacy with subjective and objective evaluations.
We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data. Our best model, a BiLSTM with highway layers using words, word probabilities, disfluency features, pause information, and a variety of acoustic features, achieves an accuracy of 84% and RSME error prediction of 4.26 on MMSE cognitive scores. While predicting cognitive decline is more challenging, our models show improvement using the multimodal approach and word probabilities, disfluency and pause information over word-only models. We show considerable gains for AD classification using multimodal fusion and gating, which can effectively deal with noisy inputs from acoustic features and ASR hypotheses.
Conversational bilingual speech encompasses three types of utterances: two purely monolingual types and one intra-sententially code-switched type. In this work, we propose a general framework to jointly model the likelihoods of the monolingual and code-switch sub-tasks that comprise bilingual speech recognition. By defining the monolingual sub-tasks with label-to-frame synchronization, our joint modeling framework can be conditionally factorized such that the final bilingual output, which may or may not be code-switched, is obtained given only monolingual information. We show that this conditionally factorized joint framework can be modeled by an end-to-end differentiable neural network. We demonstrate the efficacy of our proposed model on bilingual Mandarin-English speech recognition across both monolingual and code-switched corpora.
We propose a novel decentralized feature extraction approach in federated learning to address privacy-preservation issues for speech recognition. It is built upon a quantum convolutional neural network (QCNN) composed of a quantum circuit encoder for feature extraction, and a recurrent neural network (RNN) based end-to-end acoustic model (AM). To enhance model parameter protection in a decentralized architecture, an input speech is first up-streamed to a quantum computing server to extract Mel-spectrogram, and the corresponding convolutional features are encoded using a quantum circuit algorithm with random parameters. The encoded features are then down-streamed to the local RNN model for the final recognition. The proposed decentralized framework takes advantage of the quantum learning progress to secure models and to avoid privacy leakage attacks. Testing on the Google Speech Commands Dataset, the proposed QCNN encoder attains a competitive accuracy of 95.12\% in a decentralized model, which is better than the previous architectures using centralized RNN models with convolutional features. We also conduct an in-depth study of different quantum circuit encoder architectures to provide insights into designing QCNN-based feature extractors. Finally, neural saliency analyses demonstrate a high correlation between the proposed QCNN features, class activation maps, and the input Mel-spectrogram.
Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from the target speaker. However, it is both laborious and expensive to collect high-quality multi-lingual TTS data for the target speakers. In this paper, we proposed to use low-quality code-switched found data from the non-target speakers to achieve cross-lingual voice cloning for the target speakers. Experiments show that our proposed method can generate high-quality code-switched speech in the target voices in terms of both naturalness and speaker consistency. More importantly, we find that our method can achieve a comparable result to the state-of-the-art (SOTA) performance in cross-lingual voice cloning.
Automatic Speech Recognition (ASR) generates text which is most of the times devoid of any punctuation. Absence of punctuation is text can affect readability. Also, down stream NLP tasks such as sentiment analysis, machine translation, greatly benefit by having punctuation and sentence boundary information. We present an approach for automatic punctuation of text using a pretrained IndicBERT model. Inverse text normalization is done by hand writing weighted finite state transducer (WFST) grammars. We have developed this tool for 11 Indic languages namely Hindi, Tamil, Telugu, Kannada, Gujarati, Marathi, Odia, Bengali, Assamese, Malayalam and Punjabi. All code and data is publicly. available