Khmer text is written from left to right with optional space. Space is not served as a word boundary but instead, it is used for readability or other functional purposes. Word segmentation is a prior step for downstream tasks such as part-of-speech (POS) tagging and thus, the robustness of POS tagging highly depends on word segmentation. The conventional Khmer POS tagging is a two-stage process that begins with word segmentation and then actual tagging of each word, afterward. In this work, a joint word segmentation and POS tagging approach using a single deep learning model is proposed so that word segmentation and POS tagging can be performed spontaneously. The proposed model was trained and tested using the publicly available Khmer POS dataset. The validation suggested that the performance of the joint model is on par with the conventional two-stage POS tagging.
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech. To address this paucity, we introduce GAN-TTS, a Generative Adversarial Network for Text-to-Speech. Our architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators which operate on random windows of different sizes. The discriminators analyse the audio both in terms of general realism, as well as how well the audio corresponds to the utterance that should be pronounced. To measure the performance of GAN-TTS, we employ both subjective human evaluation (MOS - Mean Opinion Score), as well as novel quantitative metrics (Fr\'echet DeepSpeech Distance and Kernel DeepSpeech Distance), which we find to be well correlated with MOS. We show that GAN-TTS is capable of generating high-fidelity speech with naturalness comparable to the state-of-the-art models, and unlike autoregressive models, it is highly parallelisable thanks to an efficient feed-forward generator. Listen to GAN-TTS reading this abstract at https://storage.googleapis.com/deepmind-media/research/abstract.wav.
Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling has shown additional improvements by training a spatial filtering layer jointly within an acoustic model. In this paper, we further develop this idea and use frequency aligned network for robust multi-channel automatic speech recognition (ASR). Unlike an affine layer in the frequency domain, the proposed frequency aligned component prevents one frequency bin influencing other frequency bins. We show that this modification not only reduces the number of parameters in the model but also significantly and improves the ASR performance. We investigate effects of frequency aligned network through ASR experiments on the real-world far-field data where users are interacting with an ASR system in uncontrolled acoustic environments. We show that our multi-channel acoustic model with a frequency aligned network shows up to 18% relative reduction in word error rate.
In order to achieve high accuracy for machine learning (ML) applications, it is essential to employ models with a large number of parameters. Certain applications, such as Automatic Speech Recognition (ASR), however, require real-time interactions with users, hence compelling the model to have as low latency as possible. Deploying large scale ML applications thus necessitates model quantization and compression, especially when running ML models on resource constrained devices. For example, by forcing some of the model weight values into zero, it is possible to apply zero-weight compression, which reduces both the model size and model reading time from the memory. In the literature, such methods are referred to as sparse pruning. The fundamental questions are when and which weights should be forced to zero, i.e. be pruned. In this work, we propose a compressed sensing based pruning (CSP) approach to effectively address those questions. By reformulating sparse pruning as a sparsity inducing and compression-error reduction dual problem, we introduce the classic compressed sensing process into the ML model training process. Using ASR task as an example, we show that CSP consistently outperforms existing approaches in the literature.
In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior between hybrid acoustic models and neural end-to-end systems when mixing acoustic training data from several domains. For these experiments we composed a multi-domain dataset from public sources, with the different domains in the corpus covering a wide variety of topics and acoustic conditions such as telephone conversations, lectures, read speech and broadcast news. We show that for the hybrid models, supplying additional training data from other domains with mismatched acoustic conditions does not increase the performance on specific domains. However, our end-to-end models optimized with sequence-based criterion generalize better than the hybrid models on diverse domains. In term of word-error-rate performance, our experimental acoustic-to-word and attention-based models trained on multi-domain dataset reach the performance of domain-specific long short-term memory (LSTM) hybrid models, thus resulting in multi-domain speech recognition systems that do not suffer in performance over domain specific ones. Moreover, the use of neural end-to-end models eliminates the need of domain-adapted language models during recognition, which is a great advantage when the input domain is unknown.
Artificial neural networks (ANN), typically referred to as neural networks, are a class of Machine Learning algorithms and have achieved widespread success, having been inspired by the biological structure of the human brain. Neural networks are inherently powerful due to their ability to learn complex function approximations from data. This generalization ability has been able to impact multidisciplinary areas involving image recognition, speech recognition, natural language processing, and others. Activation functions are a crucial sub-component of neural networks. They define the output of a node in the network given a set of inputs. This survey discusses the main concepts of activation functions in neural networks, including; a brief introduction to deep neural networks, a summary of what are activation functions and how they are used in neural networks, their most common properties, the different types of activation functions, some of the challenges, limitations, and alternative solutions faced by activation functions, concluding with the final remarks.
Recently several papers have been published on nonlinear prediction applied to speech coding. At ICASSP98 we presented a system based on an ADPCM scheme with a nonlinear predictor based on a neural net. The most critical parameter was the training procedure in order to achieve good generalization capability and robustness against mismatch between training and testing conditions. In this paper, we propose several new approaches that improve the performance of the original system in up to 1.2dB of SEGSNR (using bayesian regularization). The variance of the SEGSNR between frames is also minimized, so the new scheme produces a more stable quality of the output.
This study investigates the speech articulatory coordination in schizophrenia subjects exhibiting strong positive symptoms (e.g. hallucinations and delusions), using two distinct channel-delay correlation methods. We show that the schizophrenic subjects with strong positive symptoms and who are markedly ill pose complex articulatory coordination pattern in facial and speech gestures than what is observed in healthy subjects. This distinction in speech coordination pattern is used to train a multimodal convolutional neural network (CNN) which uses video and audio data during speech to distinguish schizophrenic patients with strong positive symptoms from healthy subjects. We also show that the vocal tract variables (TVs) which correspond to place of articulation and glottal source outperform the Mel-frequency Cepstral Coefficients (MFCCs) when fused with Facial Action Units (FAUs) in the proposed multimodal network. For the clinical dataset we collected, our best performing multimodal network improves the mean F1 score for detecting schizophrenia by around 18% with respect to the full vocal tract coordination (FVTC) baseline method implemented with fusing FAUs and MFCCs.
This paper describes our submitted systems to the 2022 ADD challenge withing the tracks 1 and 2. Our approach is based on the combination of a pre-trained wav2vec2 feature extractor and a downstream classifier to detect spoofed audio. This method exploits the contextualized speech representations at the different transformer layers to fully capture discriminative information. Furthermore, the classification model is adapted to the application scenario using different data augmentation techniques. We evaluate our system for audio synthesis detection in both the ASVspoof 2021 and the 2022 ADD challenges, showing its robustness and good performance in realistic challenging environments such as telephonic and audio codec systems, noisy audio, and partial deepfakes.
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new speech content, and new environments. It significantly outperforms state-of-the-art baseline methods in both objective and subjective experiments.