Automatic hate speech detection in online social networks is an important open problem in Natural Language Processing (NLP). Hate speech is a multidimensional issue, strongly dependant on language and cultural factors. Despite its relevance, research on this topic has been almost exclusively devoted to English. Most supervised learning resources, such as labeled datasets and NLP tools, have been created for this same language. Considering that a large portion of users worldwide speak in languages other than English, there is an important need for creating efficient approaches for multilingual hate speech detection. In this work we propose to address the problem of multilingual hate speech detection from the perspective of transfer learning. Our goal is to determine if knowledge from one particular language can be used to classify other language, and to determine effective ways to achieve this. We propose a hate specific data representation and evaluate its effectiveness against general-purpose universal representations most of which, unlike our proposed model, have been trained on massive amounts of data. We focus on a cross-lingual setting, in which one needs to classify hate speech in one language without having access to any labeled data for that language. We show that the use of our simple yet specific multilingual hate representations improves classification results. We explain this with a qualitative analysis showing that our specific representation is able to capture some common patterns in how hate speech presents itself in different languages. Our proposal constitutes, to the best of our knowledge, the first attempt for constructing multilingual specific-task representations. Despite its simplicity, our model outperformed the previous approaches for most of the experimental setups. Our findings can orient future solutions toward the use of domain-specific representations.
While low resource speech recognition has attracted a lot of attention from the speech community, there are a few tools available to facilitate low resource speech collection. In this work, we present SANTLR: Speech Annotation Toolkit for Low Resource Languages. It is a web-based toolkit which allows researchers to easily collect and annotate a corpus of speech in a low resource language. Annotators may use this toolkit for two purposes: transcription or recording. In transcription, annotators would transcribe audio files provided by the researchers; in recording, annotators would record their voice by reading provided texts. We highlight two properties of this toolkit. First, SANTLR has a very user-friendly User Interface (UI). Both researchers and annotators may use this simple web interface to interact. There is no requirement for the annotators to have any expertise in audio or text processing. The toolkit would handle all preprocessing and postprocessing steps. Second, we employ a multi-step ranking mechanism facilitate the annotation process. In particular, the toolkit would give higher priority to utterances which are easier to annotate and are more beneficial to achieving the goal of the annotation, e.g. quickly training an acoustic model.
The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in cloud may also reveal some sensitive information. This paper proposes a deep polynomial network (DPN) that can be applied to the encrypted speech as an acoustic model. It allows clients to send their data in an encrypted form to the cloud to ensure that their data remains confidential, at mean while the DPN can still make frame-level predictions over the encrypted speech and return them in encrypted form. One good property of the DPN is that it can be trained on unencrypted speech features in the traditional way. To keep the cloud away from the raw audio and recognition results, a cloud-local joint decoding framework is also proposed. We demonstrate the effectiveness of model and framework on the Switchboard and Cortana voice assistant tasks with small performance degradation and latency increased comparing with the traditional cloud-based DNNs.
With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. Researchers and industry prefer to use end-to-end ASR systems for on-device speech recognition tasks. This is because end-to-end systems can be made resource-efficient while maintaining a higher quality compared to hybrid systems. However, building end-to-end models requires a significant amount of speech data. Another challenging task associated with speech assistants is personalization, which mainly lies in handling out-of-vocabulary (OOV) words. In this work, we consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate, embodied in Babel Turkish and Babel Georgian tasks. To address the aforementioned problems, we propose a method of dynamic acoustic unit augmentation based on the BPE-dropout technique. It non-deterministically tokenizes utterances to extend the token's contexts and to regularize their distribution for the model's recognition of unseen words. It also reduces the need for optimal subword vocabulary size search. The technique provides a steady improvement in regular and personalized (OOV-oriented) speech recognition tasks (at least 6% relative WER and 25% relative F-score) at no additional computational cost. Owing to the use of BPE-dropout, our monolingual Turkish Conformer established a competitive result with 22.2% character error rate (CER) and 38.9% word error rate (WER), which is close to the best published multilingual system.
Text-to-Speech synthesis in Indian languages has a seen lot of progress over the decade partly due to the annual Blizzard challenges. These systems assume the text to be written in Devanagari or Dravidian scripts which are nearly phonemic orthography scripts. However, the most common form of computer interaction among Indians is ASCII written transliterated text. Such text is generally noisy with many variations in spelling for the same word. In this paper we evaluate three approaches to synthesize speech from such noisy ASCII text: a naive Uni-Grapheme approach, a Multi-Grapheme approach, and a supervised Grapheme-to-Phoneme (G2P) approach. These methods first convert the ASCII text to a phonetic script, and then learn a Deep Neural Network to synthesize speech from that. We train and test our models on Blizzard Challenge datasets that were transliterated to ASCII using crowdsourcing. Our experiments on Hindi, Tamil and Telugu demonstrate that our models generate speech of competetive quality from ASCII text compared to the speech synthesized from the native scripts. All the accompanying transliterated datasets are released for public access.
Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some transcribed speech. We study whether and how visual grounding is useful in the presence of varying amounts of textual supervision. In particular, we consider the task of semantic speech retrieval in a low-resource setting. We use a previously studied data set and task, where models are trained on images with spoken captions and evaluated on human judgments of semantic relevance. We propose a multitask learning approach to leverage both visual and textual modalities, with visual supervision in the form of keyword probabilities from an external tagger. We find that visual grounding is helpful even in the presence of textual supervision, and we analyze this effect over a range of sizes of transcribed data sets. With ~5 hours of transcribed speech, we obtain 23% higher average precision when also using visual supervision.
We present STUDIES, a new speech corpus for developing a voice agent that can speak in a friendly manner. Humans naturally control their speech prosody to empathize with each other. By incorporating this "empathetic dialogue" behavior into a spoken dialogue system, we can develop a voice agent that can respond to a user more naturally. We designed the STUDIES corpus to include a speaker who speaks with empathy for the interlocutor's emotion explicitly. We describe our methodology to construct an empathetic dialogue speech corpus and report the analysis results of the STUDIES corpus. We conducted a text-to-speech experiment to initially investigate how we can develop more natural voice agent that can tune its speaking style corresponding to the interlocutor's emotion. The results show that the use of interlocutor's emotion label and conversational context embedding can produce speech with the same degree of naturalness as that synthesized by using the agent's emotion label. Our project page of the STUDIES corpus is http://sython.org/Corpus/STUDIES.
Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints and the resulting distortion that the frontend processing introduces in speech. Time-frequency masking based approaches have been shown to work well, but they need additional hyper-parameters to scale the mask to limit speech distortion. Such mask scalars are typically hand-tuned and chosen conservatively. In this work, we present a technique to predict mask scalars using an ASR-based loss in an end-to-end fashion, with minimal increase in the overall model size and complexity. We evaluate the approach on two robust ASR tasks: multichannel enhancement in the presence of speech and non-speech noise, and acoustic echo cancellation (AEC). Results show that the presented algorithm consistently improves word error rate (WER) without the need for any additional tuning over strong baselines that use hand-tuned hyper-parameters: up to 16% for multichannel enhancement in noisy conditions, and up to 7% for AEC.
In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the time-dependency modelling and time-pooling is achieved through a Self-Attention mechanism. Besides overall speech quality, the model also predicts the four speech quality dimensions Noisiness, Coloration, Discontinuity, and Loudness, and in this way gives more insight into the cause of a quality degradation. Furthermore, new datasets with over 13,000 speech files were created for training and validation of the model. The model was finally tested on a new, live-talking test dataset that contains recordings of real telephone calls. Overall, NISQA was trained and evaluated on 81 datasets from different sources and showed to provide reliable predictions also for unknown speech samples. The code, model weights, and datasets are open-sourced.
Semantic communications could improve the transmission efficiency significantly by exploring the input semantic information. Motivated by the breakthroughs in deep learning (DL), we make an effort to recover the transmitted speech signals in the semantic communication systems, which minimizes the error at the semantic level rather than the bit level or symbol level as in the traditional communication systems. Particularly, we design a DL-enabled semantic communication system for speech signals, named DeepSC-S. Based on an attention mechanism employing squeeze-and-excitation (SE) networks, DeepSC-S is able to identify the essential speech information and assign high values to the weights corresponding to the essential information when training the neural network. Moreover, in order to facilitate the proposed DeepSC-S to cater to dynamic channel environments, we dedicate to find a general model to cope with various channel conditions without retraining. Furthermore, to verify the model adaptation in practice, we investigate DeepSC-S in the telephone systems as well as the multimedia transmission systems, which usually requires higher data rates and lower transmission latency. The simulation results demonstrate that our proposed DeepSC-S achieves higher system performance than the traditional communications in both telephone systems and multimedia transmission systems by comparing the speech signals metrics, signal-to-distortion ration and perceptual evaluation of speech distortion. Besides, DeepSC-S is more robust to channel variations than the traditional approaches, especially in the low signal-to-noise (SNR) regime.