In this paper, we describe KT-Speech-Crawler: an approach for automatic dataset construction for speech recognition by crawling YouTube videos. We outline several filtering and post-processing steps, which extract samples that can be used for training end-to-end neural speech recognition systems. In our experiments, we demonstrate that a single-core version of the crawler can obtain around 150 hours of transcribed speech within a day, containing an estimated 3.5% word error rate in the transcriptions. Automatically collected samples contain reading and spontaneous speech recorded in various conditions including background noise and music, distant microphone recordings, and a variety of accents and reverberation. When training a deep neural network on speech recognition, we observed around 40\% word error rate reduction on the Wall Street Journal dataset by integrating 200 hours of the collected samples into the training set. The demo (http://emnlp-demo.lakomkin.me/) and the crawler code (https://github.com/EgorLakomkin/KTSpeechCrawler) are publicly available.
Statistical parametric speech synthesizers have recently shown their ability to produce natural-sounding and flexible voices. Unfortunately the delivered quality suffers from a typical buzziness due to the fact that speech is vocoded. This paper proposes a new excitation model in order to reduce this undesirable effect. This model is based on the decomposition of pitch-synchronous residual frames on an orthonormal basis obtained by Principal Component Analysis. This basis contains a limited number of eigenresiduals and is computed on a relatively small speech database. A stream of PCA-based coefficients is added to our HMM-based synthesizer and allows to generate the voiced excitation during the synthesis. An improvement compared to the traditional excitation is reported while the synthesis engine footprint remains under about 1Mb.
Recent progress in NLP is driven by pretrained models leveraging massive datasets and has predominantly benefited the world's political and economic superpowers. Technologically underserved languages are left behind because they lack such resources. Hundreds of underserved languages, nevertheless, have available data sources in the form of interlinear glossed text (IGT) from language documentation efforts. IGT remains underutilized in NLP work, perhaps because its annotations are only semi-structured and often language-specific. With this paper, we make the case that IGT data can be leveraged successfully provided that target language expertise is available. We specifically advocate for collaboration with documentary linguists. Our paper provides a roadmap for successful projects utilizing IGT data: (1) It is essential to define which NLP tasks can be accomplished with the given IGT data and how these will benefit the speech community. (2) Great care and target language expertise is required when converting the data into structured formats commonly employed in NLP. (3) Task-specific and user-specific evaluation can help to ascertain that the tools which are created benefit the target language speech community. We illustrate each step through a case study on developing a morphological reinflection system for the Tsimchianic language Gitksan.
Audio-based classification techniques on body sounds have long been studied to support diagnostic decisions, particularly in pulmonary diseases. In response to the urgency of the COVID-19 pandemic, a growing number of models are developed to identify COVID-19 patients based on acoustic input. Most models focus on cough because the dry cough is the best-known symptom of COVID-19. However, other body sounds, such as breath and speech, have also been revealed to correlate with COVID-19 as well. In this work, rather than relying on a specific body sound, we propose Fused Audio Instance and Representation for COVID-19 Detection (FAIR4Cov). It relies on constructing a joint feature vector obtained from a plurality of body sounds in waveform and spectrogram representation. The core component of FAIR4Cov is a self-attention fusion unit that is trained to establish the relation of multiple body sounds and audio representations and integrate it into a compact feature vector. We set up our experiments on different combinations of body sounds using only waveform, spectrogram, and a joint representation of waveform and spectrogram. Our findings show that the use of self-attention to combine extracted features from cough, breath, and speech sounds leads to the best performance with an Area Under the Receiver Operating Characteristic Curve (AUC) score of 0.8658, a sensitivity of 0.8057, and a specificity of 0.7958. This AUC is 0.0227 higher than the one of the models trained on spectrograms only and 0.0847 higher than the one of the models trained on waveforms only. The results demonstrate that the combination of spectrogram with waveform representation helps to enrich the extracted features and outperforms the models with single representation.
Generative adversarial network (GAN) still exists some problems in dealing with speech enhancement (SE) task. Some GAN-based systems adopt the same structure from Pixel-to-Pixel directly without special optimization. The importance of the generator network has not been fully explored. Other related researches change the generator network but operate in the time-frequency domain, which ignores the phase mismatch problem. In order to solve these problems, a deep complex convolution recurrent GAN (DCCRGAN) structure is proposed in this paper. The complex module builds the correlation between magnitude and phase of the waveform and has been proved to be effective. The proposed structure is trained in an end-to-end way. Different LSTM layers are used in the generator network to sufficiently explore the speech enhancement performance of DCCRGAN. The experimental results confirm that the proposed DCCRGAN outperforms the state-of-the-art GAN-based SE systems.
In this article, we investigate whispered-to natural-speech conversion method using sequence to sequence generation approach by proposing modified transformer architecture. We investigate different kinds of features such as mel frequency cepstral coefficients (MFCCs) and smoothed spectral features. The network is trained end-to-end (E2E) using supervised approach. We investigate the effectiveness of embedded auxillary decoder used after N encoder sub-layers, and is trained with the frame level objective function for identifying source phoneme labels. We predict target audio features and generate audio using these for testing. We test on standard wTIMIT dataset and CHAINS dataset. We report results as word-error-rate (WER) generated by using automatic speech recognition (ASR) system and also BLEU scores. %intelligibility and naturalness using mean opinion score and additionally using word error rate using automatic speech recognition system. In addition, we measure spectral shape of an output speech signal by measuring formant distributions w.r.t the reference speech signal, at frame level. In relation to this aspect, we also found that the whispered-to-natural converted speech formants probability distribution is closer to ground truth distribution. To the authors' best knowledge, this is the first time transformer with auxiliary decoder has been applied for whispered-to-natural speech conversion. [This pdf is TASLP submission draft version 1.0, 14th April 2020.]
Mispronunciation detection and diagnosis (MDD) technology is a key component of computer-assisted pronunciation training system (CAPT). In the field of assessing the pronunciation quality of constrained speech, the given transcriptions can play the role of a teacher. Conventional methods have fully utilized the prior texts for the model construction or improving the system performance, e.g. forced-alignment and extended recognition networks. Recently, some end-to-end based methods attempt to incorporate the prior texts into model training and preliminarily show the effectiveness. However, previous studies mostly consider applying raw attention mechanism to fuse audio representations with text representations, without taking possible text-pronunciation mismatch into account. In this paper, we present a gating strategy that assigns more importance to the relevant audio features while suppressing irrelevant text information. Moreover, given the transcriptions, we design an extra contrastive loss to reduce the gap between the learning objective of phoneme recognition and MDD. We conducted experiments using two publicly available datasets (TIMIT and L2-Arctic) and our best model improved the F1 score from $57.51\%$ to $61.75\%$ compared to the baselines. Besides, we provide a detailed analysis to shed light on the effectiveness of gating mechanism and contrastive learning on MDD.
We propose a non-invasive and cost-effective method to automatically detect dementia by utilizing solely speech audio data without any linguistic features. We extract paralinguistic features for a short speech utterance segment and use Gated Convolutional Neural Networks (GCNN) to classify it into dementia or healthy. We evaluate our method by using the Pitt Corpus and our own dataset, the PROMPT Database. Our method yields the accuracy of 73.1% on the Pitt Corpus using an average of 114 seconds of speech data. In the PROMPT Database, our method yields the accuracy of 74.7% using 4 seconds of speech data and it improves to 79.0% when we use 5 minutes of speech data. Furthermore, we evaluate our method on a three-class classification problem in which we included the Mild Cognitive Impairment (MCI) class and achieved the accuracy of 60.6%.
Face-to-face speech data collection has been next to impossible globally due to COVID-19 restrictions. To address this problem, simultaneous recordings of three repetitions of the cardinal vowels were made using a Zoom H6 Handy Recorder with external microphone (henceforth H6) and compared with two alternatives accessible to potential participants at home: the Zoom meeting application (henceforth Zoom) and two lossless mobile phone applications (Awesome Voice Recorder, and Recorder; henceforth Phone). F0 was tracked accurately by all devices; however, for formant analysis (F1, F2, F3) Phone performed better than Zoom, i.e. more similarly to H6. Zoom recordings also exhibited unexpected drops in intensity. The results suggest that lossless format phone recordings present a viable option for at least some phonetic studies.
In this paper we present our approach for detecting signs of depression from social media text. Our model relies on word unigrams, part-of-speech tags, readabilitiy measures and the use of first, second or third person and the number of words. Our best model obtained a macro F1-score of 0.439 and ranked 25th, out of 31 teams. We further take advantage of the interpretability of the Logistic Regression model and we make an attempt to interpret the model coefficients with the hope that these will be useful for further research on the topic.