Speech enhancement and separation have been a long-standing problem, especially with the recent advances using a single microphone. Although microphones perform well in constrained settings, their performance for speech separation decreases in noisy conditions. In this work, we propose RadioSES, an audioradio speech enhancement and separation system that overcomes inherent problems in audio-only systems. By fusing a complementary radio modality, RadioSES can estimate the number of speakers, solve source association problem, separate and enhance noisy mixture speeches, and improve both intelligibility and perceptual quality. We perform millimeter-wave sensing to detect and localize speakers, and introduce an audioradio deep learning framework to fuse the separate radio features with the mixed audio features. Extensive experiments using commercial off-the-shelf devices show that RadioSES outperforms a variety of state-of-the-art baselines, with consistent performance gains in different environmental settings. Compared with the audiovisual methods, RadioSES provides similar improvements (e.g., ~3 dB gains in SiSDR), along with the benefits of lower computational complexity and being less privacy concerning.
Construction of dictionaries using nonnegative matrix factorisation (NMF) has extensive applications in signal processing and machine learning. With the advances in deep learning, training compact and robust dictionaries using deep neural networks, i.e., dictionaries of deep features, has been proposed. In this study, we propose a probabilistic generative model which employs a variational autoencoder (VAE) to perform nonnegative dictionary learning. In contrast to the existing VAE models, we cast the model under a statistical framework with latent variables obeying a Gamma distribution and design a new loss function to guarantee the nonnegative dictionaries. We adopt an acceptance-rejection sampling reparameterization trick to update the latent variables iteratively. We apply the dictionaries learned from VAE-NMF to two signal processing tasks, i.e., enhancement of speech and extraction of muscle synergies. Experimental results demonstrate that VAE-NMF performs better in learning the latent nonnegative dictionaries in comparison with state-of-the-art methods.
Recent advances in self-supervision have dramatically improved the quality of speech representations. However, deployment of state-of-the-art embedding models on devices has been restricted due to their limited public availability and large resource footprint. Our work addresses these issues by publicly releasing a collection of paralinguistic speech models that are small and near state-of-the-art performance. Our approach is based on knowledge distillation, and our models are distilled on public data only. We explore different architectures and thoroughly evaluate our models on the Non-Semantic Speech (NOSS) benchmark. Our largest distilled model is less than 15% the size of the original model (314MB vs 2.2GB), achieves over 96% the accuracy on 6 of 7 tasks, and is trained on 6.5% the data. The smallest model is 1% in size (22MB) and achieves over 90% the accuracy on 6 of 7 tasks. Our models outperform the open source Wav2Vec 2.0 model on 6 of 7 tasks, and our smallest model outperforms the open source Wav2Vec 2.0 on both emotion recognition tasks despite being 7% the size.
The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural due to cut-copy-paste operation. In addition, it is not obvious how to synthesize records according to a new word not appearing in the transcript. This paper proposes a novel end-to-end text-based speech editing method called context-aware mask prediction network (CampNet). The model can simulate the text-based speech editing process by randomly masking part of speech and then predicting the masked region by sensing the speech context. It can solve unnatural prosody in the edited region and synthesize the speech corresponding to the unseen words in the transcript. Secondly, for the possible operation of text-based speech editing, we design three text-based operations based on CampNet: deletion, insertion, and replacement. These operations can cover various situations of speech editing. Thirdly, to synthesize the speech corresponding to long text in insertion and replacement operations, a word-level autoregressive generation method is proposed. Fourthly, we propose a speaker adaptation method using only one sentence for CampNet and explore the ability of few-shot learning based on CampNet, which provides a new idea for speech forgery tasks. The subjective and objective experiments on VCTK and LibriTTS datasets show that the speech editing results based on CampNet are better than TTS technology, manual editing, and VoCo method. We also conduct detailed ablation experiments to explore the effect of the CampNet structure on its performance. Finally, the experiment shows that speaker adaptation with only one sentence can further improve the naturalness of speech. Examples of generated speech can be found at https://hairuo55.github.io/CampNet.
We present automatic speech recognition (ASR) systems for Tamil and Kannada based on subword modeling to effectively handle unlimited vocabulary due to the highly agglutinative nature of the languages. We explore byte pair encoding (BPE), and proposed a variant of this algorithm named extended-BPE, and Morfessor tool to segment each word as subwords. We have effectively incorporated maximum likelihood (ML) and Viterbi estimation techniques with weighted finite state transducers (WFST) framework in these algorithms to learn the subword dictionary from a large text corpus. Using the learnt subword dictionary, the words in training data transcriptions are segmented to subwords and we train deep neural network ASR systems which recognize subword sequence for any given test speech utterance. The output subword sequence is then post-processed using deterministic rules to get the final word sequence such that the actual number of words that can be recognized is much larger. For Tamil ASR, We use 152 hours of data for training and 65 hours for testing, whereas for Kannada ASR, we use 275 hours for training and 72 hours for testing. Upon experimenting with different combination of segmentation and estimation techniques, we find that the word error rate (WER) reduces drastically when compared to the baseline word-level ASR, achieving a maximum absolute WER reduction of 6.24% and 6.63% for Tamil and Kannada respectively.
Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre-train a Transformer encoder to learn deep representations from audio data, with objectives predicting either elements from latent vector quantized space or pre-generated labels (known as target codes) with offline clustering. However, those training signals (quantized elements or codes) are independent across different tokens without considering their relations. According to our observation and analysis, the target codes share obvious patterns aligned with phonemized text data. Based on that, we propose to leverage those patterns to better pre-train the model considering the relations among the codes. The patterns we extracted, called "acoustic piece"s, are from the sentence piece result of HuBERT codes. With the acoustic piece as the training signal, we can implicitly bridge the input audio and natural language, which benefits audio-to-text tasks, such as automatic speech recognition (ASR). Simple but effective, our method "HuBERT-AP" significantly outperforms strong baselines on the LibriSpeech ASR task.
Due to the sheer volume of online hate, the AI and NLP communities have started building models to detect such hateful content. Recently, multilingual hate is a major emerging challenge for automated detection where code-mixing or more than one language have been used for conversation in social media. Typically, hate speech detection models are evaluated by measuring their performance on the held-out test data using metrics such as accuracy and F1-score. While these metrics are useful, it becomes difficult to identify using them where the model is failing, and how to resolve it. To enable more targeted diagnostic insights of such multilingual hate speech models, we introduce a set of functionalities for the purpose of evaluation. We have been inspired to design this kind of functionalities based on real-world conversation on social media. Considering Hindi as a base language, we craft test cases for each functionality. We name our evaluation dataset HateCheckHIn. To illustrate the utility of these functionalities , we test state-of-the-art transformer based m-BERT model and the Perspective API.
It was shown in our earlier work that the measurement error in the microphone position affected the room impulse response (RIR) which in turn affected the single-channel close microphone and multi-channel distant microphone speech recognition. In this paper, as an extension, we systematically study to identify the optimal location of the microphone, given an approximate and hence erroneous location of the microphone in 3D space. The primary idea is to use Monte-Carlo technique to generate a large number of random microphone positions around the erroneous microphone position and select the microphone position that results in the best performance of a general purpose automatic speech recognition (gp-asr). We experiment with clean and noisy speech and show that the optimal location of the microphone is unique and is affected by noise.
Converting written texts into their spoken forms is an essential problem in any text-to-speech (TTS) systems. However, building an effective text normalization solution for a real-world TTS system face two main challenges: (1) the semantic ambiguity of non-standard words (NSWs), e.g., numbers, dates, ranges, scores, abbreviations, and (2) transforming NSWs into pronounceable syllables, such as URL, email address, hashtag, and contact name. In this paper, we propose a new two-phase normalization approach to deal with these challenges. First, a model-based tagger is designed to detect NSWs. Then, depending on NSW types, a rule-based normalizer expands those NSWs into their final verbal forms. We conducted three empirical experiments for NSW detection using Conditional Random Fields (CRFs), BiLSTM-CNN-CRF, and BERT-BiGRU-CRF models on a manually annotated dataset including 5819 sentences extracted from Vietnamese news articles. In the second phase, we propose a forward lexicon-based maximum matching algorithm to split down the hashtag, email, URL, and contact name. The experimental results of the tagging phase show that the average F1 scores of the BiLSTM-CNN-CRF and CRF models are above 90.00%, reaching the highest F1 of 95.00% with the BERT-BiGRU-CRF model. Overall, our approach has low sentence error rates, at 8.15% with CRF and 7.11% with BiLSTM-CNN-CRF taggers, and only 6.67% with BERT-BiGRU-CRF tagger.
Automatic Part-of-speech (POS) tagging is a preprocessing step of many natural language processing (NLP) tasks such as name entity recognition (NER), speech processing, information extraction, word sense disambiguation, and machine translation. It has already gained a promising result in English and European languages, but in Indian languages, particularly in Odia language, it is not yet well explored because of the lack of supporting tools, resources, and morphological richness of language. Unfortunately, we were unable to locate an open source POS tagger for Odia, and only a handful of attempts have been made to develop POS taggers for Odia language. The main contribution of this research work is to present a conditional random field (CRF) and deep learning-based approaches (CNN and Bidirectional Long Short-Term Memory) to develop Odia part-of-speech tagger. We used a publicly accessible corpus and the dataset is annotated with the Bureau of Indian Standards (BIS) tagset. However, most of the languages around the globe have used the dataset annotated with Universal Dependencies (UD) tagset. Hence, to maintain uniformity Odia dataset should use the same tagset. So we have constructed a simple mapping from BIS tagset to UD tagset. We experimented with various feature set inputs to the CRF model, observed the impact of constructed feature set. The deep learning-based model includes Bi-LSTM network, CNN network, CRF layer, character sequence information, and pre-trained word vector. Character sequence information was extracted by using convolutional neural network (CNN) and Bi-LSTM network. Six different combinations of neural sequence labelling models are implemented, and their performance measures are investigated. It has been observed that Bi-LSTM model with character sequence feature and pre-trained word vector achieved a significant state-of-the-art result.